diff --git a/README.md b/README.md index 7be5fc7f47d5db027d120b8024982df93db95b74..59907a2f1365755b34215a094b0afe097b380640 100644 --- a/README.md +++ b/README.md @@ -1,3 +1 @@ ---- -license: mit ---- +# HEllo World \ No newline at end of file diff --git a/app/ai4bharat/transliteration/__init__.py b/app/ai4bharat/transliteration/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e66821e504c5d756b40e6942827e353ee6ee58a9 --- /dev/null +++ b/app/ai4bharat/transliteration/__init__.py @@ -0,0 +1,2 @@ +from .xlit_src import XlitEngine +from .__metadata import * diff --git a/app/ai4bharat/transliteration/__metadata.py b/app/ai4bharat/transliteration/__metadata.py new file mode 100644 index 0000000000000000000000000000000000000000..0b2f79dbba691ee60677ebe094adf0c1f246dce1 --- /dev/null +++ b/app/ai4bharat/transliteration/__metadata.py @@ -0,0 +1 @@ +__version__ = "1.1.3" diff --git a/app/ai4bharat/transliteration/transformer/__init__.py b/app/ai4bharat/transliteration/transformer/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..adc84a88358e8b99d3abd765e7a3f7de02fc1149 --- /dev/null +++ b/app/ai4bharat/transliteration/transformer/__init__.py @@ -0,0 +1,2 @@ +from .en2indic import XlitEngineTransformer_En2Indic +from .indic2en import XlitEngineTransformer_Indic2En diff --git a/app/ai4bharat/transliteration/transformer/base_engine.py b/app/ai4bharat/transliteration/transformer/base_engine.py new file mode 100644 index 0000000000000000000000000000000000000000..afb2bfe18823566ee4c343e722c57129009de680 --- /dev/null +++ b/app/ai4bharat/transliteration/transformer/base_engine.py @@ -0,0 +1,395 @@ +import os +import re +import tqdm +import ujson +from pydload import dload +import zipfile +from abc import ABC, abstractmethod, abstractproperty +from indicnlp.normalize.indic_normalize import IndicNormalizerFactory +from urduhack import normalize as shahmukhi_normalize + +from ..utils import * +LANG_WORD_REGEXES = { + lang_name: re.compile(f"[{SCRIPT_CODE_TO_UNICODE_CHARS_RANGE_STR[script_name]}]+") + for lang_name, script_name in LANG_CODE_TO_SCRIPT_CODE.items() +} + +MODEL_FILE = 'transformer/indicxlit.pt' +DICTS_FOLDER = 'word_prob_dicts' +CHARS_FOLDER = 'corpus-bin' +DICT_FILE_FORMAT = '%s_word_prob_dict.json' +LANG_LIST_FILE = '../lang_list.txt' + +normalizer_factory = IndicNormalizerFactory() + +class BaseEngineTransformer(ABC): + + @abstractproperty + def all_supported_langs(self): + pass + + @abstractproperty + def tgt_langs(self): + pass + + def __init__(self, models_path, beam_width, rescore): + # added by yash + + print("Initializing Multilingual model for transliteration") + if 'en' in self.tgt_langs: + lang_pairs_csv = ','.join([lang+"-en" for lang in self.all_supported_langs]) + else: + lang_pairs_csv = ','.join(["en-"+lang for lang in self.all_supported_langs]) + + # initialize the model + from .custom_interactive import Transliterator + self.transliterator = Transliterator( + os.path.join(models_path, CHARS_FOLDER), + os.path.join(models_path, MODEL_FILE), + lang_pairs_csv = lang_pairs_csv, + lang_list_file = os.path.join(models_path, LANG_LIST_FILE), + beam = beam_width, batch_size = 32, + ) + + self.beam_width = beam_width + self._rescore = rescore + if self._rescore: + # loading the word_prob_dict for rescoring module + dicts_folder = os.path.join(models_path, DICTS_FOLDER) + self.word_prob_dicts = {} + for la in tqdm.tqdm(self.tgt_langs, desc="Loading dicts into RAM"): + self.word_prob_dicts[la] = ujson.load(open( + os.path.join(dicts_folder, DICT_FILE_FORMAT%la) + )) + + def download_models(self, models_path, download_url): + ''' + Download models from bucket + ''' + # added by yash + model_file_path = os.path.join(models_path, MODEL_FILE) + if not os.path.isfile(model_file_path): + print('Downloading Multilingual model for transliteration') + remote_url = download_url + downloaded_zip_path = os.path.join(models_path, 'model.zip') + + dload(url=remote_url, save_to_path=downloaded_zip_path, max_time=None) + + if not os.path.isfile(downloaded_zip_path): + exit(f'ERROR: Unable to download model from {remote_url} into {models_path}') + + with zipfile.ZipFile(downloaded_zip_path, 'r') as zip_ref: + zip_ref.extractall(models_path) + + if os.path.isfile(model_file_path): + os.remove(downloaded_zip_path) + else: + exit(f'ERROR: Unable to find models in {models_path} after download') + + print("Models downloaded to:", models_path) + print("NOTE: When uninstalling this library, REMEMBER to delete the models manually") + return model_file_path + + def download_dicts(self, models_path, download_url): + ''' + Download language model probablitites dictionaries + ''' + dicts_folder = os.path.join(models_path, DICTS_FOLDER) + if not os.path.isdir(dicts_folder): + # added by yash + print('Downloading language model probablitites dictionaries for rescoring module') + remote_url = download_url + downloaded_zip_path = os.path.join(models_path, 'dicts.zip') + + dload(url=remote_url, save_to_path=downloaded_zip_path, max_time=None) + + if not os.path.isfile(downloaded_zip_path): + exit(f'ERROR: Unable to download model from {remote_url} into {models_path}') + + with zipfile.ZipFile(downloaded_zip_path, 'r') as zip_ref: + zip_ref.extractall(models_path) + + if os.path.isdir(dicts_folder): + os.remove(downloaded_zip_path) + else: + exit(f'ERROR: Unable to find models in {models_path} after download') + return dicts_folder + + def indic_normalize(self, words, lang_code): + if lang_code not in ['gom', 'ks', 'ur', 'mai', 'brx', 'mni']: + normalizer = normalizer_factory.get_normalizer(lang_code) + words = [ normalizer.normalize(word) for word in words ] + + if lang_code in ['mai', 'brx' ]: + normalizer = normalizer_factory.get_normalizer('hi') + words = [ normalizer.normalize(word) for word in words ] + + + if lang_code in [ 'ur' ]: + words = [ shahmukhi_normalize(word) for word in words ] + + if lang_code == 'gom': + normalizer = normalizer_factory.get_normalizer('kK') + words = [ normalizer.normalize(word) for word in words ] + + # normalize and tokenize the words + # words = self.normalize(words) + + # manully mapping certain characters + # words = self.hard_normalizer(words) + return words + + def pre_process(self, words, src_lang, tgt_lang): + # TODO: Move normalize outside to efficiently perform at sentence-level + + if src_lang != 'en': + self.indic_normalize(words, src_lang) + + # convert the word into sentence which contains space separated chars + words = [' '.join(list(word.lower())) for word in words] + + lang_code = tgt_lang if src_lang == 'en' else src_lang + # adding language token + words = ['__'+ lang_code +'__ ' + word for word in words] + + return words + + def rescore(self, res_dict, result_dict, tgt_lang, alpha ): + + alpha = alpha + # word_prob_dict = {} + word_prob_dict = self.word_prob_dicts[tgt_lang] + + candidate_word_prob_norm_dict = {} + candidate_word_result_norm_dict = {} + + input_data = {} + for i in res_dict.keys(): + input_data[res_dict[i]['S']] = [] + for j in range(len(res_dict[i]['H'])): + input_data[res_dict[i]['S']].append( res_dict[i]['H'][j][0] ) + + for src_word in input_data.keys(): + candidates = input_data[src_word] + + candidates = [' '.join(word.split(' ')) for word in candidates] + + total_score = 0 + + if src_word.lower() in result_dict.keys(): + for candidate_word in candidates: + if candidate_word in result_dict[src_word.lower()].keys(): + total_score += result_dict[src_word.lower()][candidate_word] + + candidate_word_result_norm_dict[src_word.lower()] = {} + + for candidate_word in candidates: + candidate_word_result_norm_dict[src_word.lower()][candidate_word] = (result_dict[src_word.lower()][candidate_word]/total_score) + + candidates = [''.join(word.split(' ')) for word in candidates ] + + total_prob = 0 + + for candidate_word in candidates: + if candidate_word in word_prob_dict.keys(): + total_prob += word_prob_dict[candidate_word] + + candidate_word_prob_norm_dict[src_word.lower()] = {} + for candidate_word in candidates: + if candidate_word in word_prob_dict.keys(): + candidate_word_prob_norm_dict[src_word.lower()][candidate_word] = (word_prob_dict[candidate_word]/total_prob) + + output_data = {} + for src_word in input_data.keys(): + + temp_candidates_tuple_list = [] + candidates = input_data[src_word] + candidates = [ ''.join(word.split(' ')) for word in candidates] + + + for candidate_word in candidates: + if candidate_word in word_prob_dict.keys(): + temp_candidates_tuple_list.append((candidate_word, alpha*candidate_word_result_norm_dict[src_word.lower()][' '.join(list(candidate_word))] + (1-alpha)*candidate_word_prob_norm_dict[src_word.lower()][candidate_word] )) + else: + temp_candidates_tuple_list.append((candidate_word, 0 )) + + temp_candidates_tuple_list.sort(key = lambda x: x[1], reverse = True ) + + temp_candidates_list = [] + for cadidate_tuple in temp_candidates_tuple_list: + temp_candidates_list.append(' '.join(list(cadidate_tuple[0]))) + + output_data[src_word] = temp_candidates_list + + return output_data + + def post_process(self, translation_str, tgt_lang): + lines = translation_str.split('\n') + + list_s = [line for line in lines if 'S-' in line] + # list_t = [line for line in lines if 'T-' in line] + list_h = [line for line in lines if 'H-' in line] + # list_d = [line for line in lines if 'D-' in line] + + list_s.sort(key = lambda x: int(x.split('\t')[0].split('-')[1]) ) + # list_t.sort(key = lambda x: int(x.split('\t')[0].split('-')[1]) ) + list_h.sort(key = lambda x: int(x.split('\t')[0].split('-')[1]) ) + # list_d.sort(key = lambda x: int(x.split('\t')[0].split('-')[1]) ) + + res_dict = {} + for s in list_s: + s_id = int(s.split('\t')[0].split('-')[1]) + + res_dict[s_id] = { 'S' : s.split('\t')[1] } + + # for t in list_t: + # t_id = int(t.split('\t')[0].split('-')[1]) + # if s_id == t_id: + # res_dict[s_id]['T'] = t.split('\t')[1] + + res_dict[s_id]['H'] = [] + # res_dict[s_id]['D'] = [] + + for h in list_h: + h_id = int(h.split('\t')[0].split('-')[1]) + + if s_id == h_id: + res_dict[s_id]['H'].append( ( h.split('\t')[2], pow(2,float(h.split('\t')[1])) ) ) + + # for d in list_d: + # d_id = int(d.split('\t')[0].split('-')[1]) + + # if s_id == d_id: + # res_dict[s_id]['D'].append( ( d.split('\t')[2], pow(2,float(d.split('\t')[1])) ) ) + + for r in res_dict.keys(): + res_dict[r]['H'].sort(key = lambda x : float(x[1]) ,reverse =True) + # res_dict[r]['D'].sort(key = lambda x : float(x[1]) ,reverse =True) + + + # for rescoring + result_dict = {} + for i in res_dict.keys(): + result_dict[res_dict[i]['S']] = {} + for j in range(len(res_dict[i]['H'])): + result_dict[res_dict[i]['S']][res_dict[i]['H'][j][0]] = res_dict[i]['H'][j][1] + + + transliterated_word_list = [] + if self._rescore: + output_dir = self.rescore(res_dict, result_dict, tgt_lang, alpha = 0.9) + for src_word in output_dir.keys(): + for j in range(len(output_dir[src_word])): + transliterated_word_list.append( output_dir[src_word][j] ) + + else: + for i in res_dict.keys(): + # transliterated_word_list.append( res_dict[i]['S'] + ' : ' + res_dict[i]['H'][0][0] ) + for j in range(len(res_dict[i]['H'])): + transliterated_word_list.append( res_dict[i]['H'][j][0] ) + + # remove extra spaces + # transliterated_word_list = [''.join(pair.split(':')[0].split(' ')[1:]) + ' : ' + ''.join(pair.split(':')[1].split(' ')) for pair in transliterated_word_list] + + transliterated_word_list = [''.join(word.split(' ')) for word in transliterated_word_list] + + return transliterated_word_list + + def _transliterate_word(self, text, src_lang, tgt_lang, topk=4, nativize_punctuations=True, nativize_numerals=False): + if not text: + return text + text = text.lower().strip() + + if src_lang != 'en': + # Our model does not transliterate native punctuations or numerals + # So process them first so that they are not considered for transliteration + text = text.translate(INDIC_TO_LATIN_PUNCT_TRANSLATOR) + text = text.translate(INDIC_TO_STANDARD_NUMERALS_TRANSLATOR) + else: + # Transliterate punctuations & numerals if tgt_lang is Indic + if nativize_punctuations: + if tgt_lang in RTL_LANG_CODES: + text = text.translate(LATIN_TO_PERSOARABIC_PUNC_TRANSLATOR) + text = nativize_latin_fullstop(text, tgt_lang) + if nativize_numerals: + text = text.translate(LATIN_TO_NATIVE_NUMERALS_TRANSLATORS[tgt_lang]) + + matches = LANG_WORD_REGEXES[src_lang].findall(text) + + if not matches: + return [text] + + src_word = matches[-1] + + transliteration_list = self.batch_transliterate_words([src_word], src_lang, tgt_lang, topk=topk)[0] + + if tgt_lang != 'en' or tgt_lang != 'sa': + # If users want to avoid yuktAkshara, this is facilitated by allowing them to type subwords inorder to construct a word + # For example, "ଜନ୍‍ସନ୍‍ଙ୍କୁ" can be written by "ଜନ୍‍" + "ସନ୍‍" + "କୁ" + # Not enabled for Sanskrit, as sandhi compounds are generally written word-by-word + for i in range(len(transliteration_list)): + transliteration_list[i] = hardfix_wordfinal_virama(transliteration_list[i]) + + if src_word == text: + return transliteration_list + + return [ + rreplace(text, src_word, tgt_word) + for tgt_word in transliteration_list + ] + + def batch_transliterate_words(self, words, src_lang, tgt_lang, topk=4): + perprcossed_words = self.pre_process(words, src_lang, tgt_lang) + translation_str = self.transliterator.translate(perprcossed_words, nbest=topk) + + # FIXME: Handle properly in `post_process()` to return results for all words + transliteration_list = self.post_process(translation_str, tgt_lang) + + # Lang-specific patches. TODO: Move to indic-nlp-library + if tgt_lang == 'mr': + for i in range(len(transliteration_list)): + transliteration_list[i] = transliteration_list[i].replace("अॅ", 'ॲ') + + if tgt_lang == 'or': + for i in range(len(transliteration_list)): + transliteration_list[i] = fix_odia_confusing_ambiguous_yuktakshara(transliteration_list[i]) + + if tgt_lang == 'sa': + for i in range(len(transliteration_list)): + transliteration_list[i] = explicit_devanagari_wordfinal_schwa_delete(words[0], transliteration_list[i]) + # Retain only unique, preserving order + transliteration_list = list(dict.fromkeys(transliteration_list)) + + return [transliteration_list] + + def _transliterate_sentence(self, text, src_lang, tgt_lang, nativize_punctuations=True, nativize_numerals=False): + # TODO: Minimize code redundancy with `_transliterate_word()` + + if not text: + return text + text = text.lower().strip() + + if src_lang != 'en': + # Our model does not transliterate native punctuations or numerals + # So process them first so that they are not considered for transliteration + text = text.translate(INDIC_TO_LATIN_PUNCT_TRANSLATOR) + text = text.translate(INDIC_TO_STANDARD_NUMERALS_TRANSLATOR) + else: + # Transliterate punctuations & numerals if tgt_lang is Indic + if nativize_punctuations: + if tgt_lang in RTL_LANG_CODES: + text = text.translate(LATIN_TO_PERSOARABIC_PUNC_TRANSLATOR) + text = nativize_latin_fullstop(text, tgt_lang) + if nativize_numerals: + text = text.translate(LATIN_TO_NATIVE_NUMERALS_TRANSLATORS[tgt_lang]) + + matches = LANG_WORD_REGEXES[src_lang].findall(text) + + if not matches: + return text + + out_str = text + for match in matches: + result = self.batch_transliterate_words([match], src_lang, tgt_lang)[0][0] + out_str = re.sub(match, result, out_str, 1) + return out_str diff --git a/app/ai4bharat/transliteration/transformer/custom_interactive.py b/app/ai4bharat/transliteration/transformer/custom_interactive.py new file mode 100644 index 0000000000000000000000000000000000000000..91628b0a55b5328f626f0fe19694e35dcbfa3a09 --- /dev/null +++ b/app/ai4bharat/transliteration/transformer/custom_interactive.py @@ -0,0 +1,354 @@ +#!/usr/bin/env python3 -u +# Copyright (c) Facebook, Inc. and its affiliates. +# +# This source code is licensed under the MIT license found in the +# LICENSE file in the root directory of this source tree. +""" +Translate raw text with a trained model. Batches data on-the-fly. +""" + +import ast +import fileinput +import logging +import math +import os +import sys +import time +from argparse import Namespace +from collections import namedtuple + +import numpy as np +import torch + +from fairseq import checkpoint_utils, distributed_utils, options, tasks, utils +from fairseq.dataclass.configs import FairseqConfig +from fairseq.dataclass.utils import convert_namespace_to_omegaconf +from fairseq.token_generation_constraints import pack_constraints, unpack_constraints +from fairseq_cli.generate import get_symbols_to_strip_from_output + +Batch = namedtuple("Batch", "ids src_tokens src_lengths constraints") +Translation = namedtuple("Translation", "src_str hypos pos_scores alignments") + +def make_batches(lines, cfg, task, max_positions, encode_fn): + def encode_fn_target(x): + return encode_fn(x) + + + if cfg.generation.constraints: + # Strip (tab-delimited) contraints, if present, from input lines, + # store them in batch_constraints + batch_constraints = [list() for _ in lines] + for i, line in enumerate(lines): + if "\t" in line: + lines[i], *batch_constraints[i] = line.split("\t") + + # Convert each List[str] to List[Tensor] + for i, constraint_list in enumerate(batch_constraints): + batch_constraints[i] = [ + task.target_dictionary.encode_line( + encode_fn_target(constraint), + append_eos=False, + add_if_not_exist=False, + ) + for constraint in constraint_list + ] + + if cfg.generation.constraints: + constraints_tensor = pack_constraints(batch_constraints) + else: + constraints_tensor = None + + tokens, lengths = task.get_interactive_tokens_and_lengths(lines, encode_fn) + + itr = task.get_batch_iterator( + dataset=task.build_dataset_for_inference( + tokens, lengths, constraints=constraints_tensor + ), + max_tokens=cfg.dataset.max_tokens, + max_sentences=cfg.dataset.batch_size, + max_positions=max_positions, + ignore_invalid_inputs=cfg.dataset.skip_invalid_size_inputs_valid_test, + ).next_epoch_itr(shuffle=False) + for batch in itr: + ids = batch["id"] + src_tokens = batch["net_input"]["src_tokens"] + src_lengths = batch["net_input"]["src_lengths"] + constraints = batch.get("constraints", None) + + yield Batch( + ids=ids, + src_tokens=src_tokens, + src_lengths=src_lengths, + constraints=constraints, + ) + + +# added +class Transliterator: + def __init__( + self, data_bin_dir, model_checkpoint_path, lang_pairs_csv, lang_list_file, beam, batch_size = 32, + ): + + self.parser = options.get_interactive_generation_parser() + + # buffer_size is currently not used but we just initialize it to batch + # size + 1 to avoid any assertion errors. + + self.parser.set_defaults( + path = model_checkpoint_path, + num_wokers = -1, + batch_size = batch_size, + buffer_size = batch_size + 1, + task = "translation_multi_simple_epoch", + beam = beam, + # nbest = nbest, + # source_lang = 'en' , + # target_lang = 'mlt' , + # encoder_langtok = "tgt" , + # lang_dict = "lang_list.txt" + ) + + self.args = options.parse_args_and_arch(self.parser, input_args = [data_bin_dir] ) + + self.args.skip_invalid_size_inputs_valid_test = False + # self.args.lang_pairs = "en-as,en-bn,en-gom,en-gu,en-hi,en-kn,en-ks,en-mai,en-ml,en-mr,en-ne,en-or,en-pa,en-sa,en-sd,en-si,en-ta,en-te,en-ur" + self.args.lang_pairs = lang_pairs_csv + # self.args.source_lang = 'en' + # self.args.target_lang = 'bn' + # self.args.encoder_langtok = 'tgt' + self.args.lang_dict = lang_list_file + + self.cfg = convert_namespace_to_omegaconf(self.args) + + if isinstance(self.cfg, Namespace): + self.cfg = convert_namespace_to_omegaconf(self.cfg) + + # start_time = time.time() + self.total_translate_time = 0 + + utils.import_user_module(self.cfg.common) + + if self.cfg.interactive.buffer_size < 1: + self.cfg.interactive.buffer_size = 1 + if self.cfg.dataset.max_tokens is None and self.cfg.dataset.batch_size is None: + self.cfg.dataset.batch_size = 1 + + assert ( + not self.cfg.generation.sampling or self.cfg.generation.nbest == self.cfg.generation.beam + ), "--sampling requires --nbest to be equal to --beam" + assert ( + not self.cfg.dataset.batch_size + or self.cfg.dataset.batch_size <= self.cfg.interactive.buffer_size + ), "--batch-size cannot be larger than --buffer-size" + + + # FIXME: Following lines are commented out by GokulNC due to some erros on CPU + # GokulNC: Why do we need seeding for inference? What is stochastic decoding? + + # # Fix seed for stochastic decoding + # if self.cfg.common.seed is not None and not self.cfg.generation.no_seed_provided: + # np.random.seed(self.cfg.common.seed) + # utils.set_torch_seed(self.cfg.common.seed) + + self.use_cuda = torch.cuda.is_available() and not self.cfg.common.cpu + + # Setup task, e.g., translation + self.task = tasks.setup_task(self.cfg.task) + + # Load ensemble + overrides = ast.literal_eval(self.cfg.common_eval.model_overrides) + # logger.info("loading model(s) from {}".format(self.cfg.common_eval.path)) + self.models, _model_args = checkpoint_utils.load_model_ensemble( + utils.split_paths(self.cfg.common_eval.path), + arg_overrides=overrides, + task=self.task, + suffix=self.cfg.checkpoint.checkpoint_suffix, + strict=(self.cfg.checkpoint.checkpoint_shard_count == 1), + num_shards=self.cfg.checkpoint.checkpoint_shard_count, + ) + + # Set dictionaries + self.src_dict = self.task.source_dictionary + self.tgt_dict = self.task.target_dictionary + + # print("src dict",self.src_dict) + # print("src dict",self.tgt_dict) + # print("self.src_dict.__len__() : ",self.src_dict.symbols) + # print("self.src_dict.__len__() : ",self.tgt_dict.symbols) + + # self.cfg.common.fp16 = True + # Optimize ensemble for generation + for i in range(len(self.models)): + if self.models[i] is None: + continue + if self.cfg.common.fp16: + self.models[i].half() + + if self.use_cuda and not self.cfg.distributed_training.pipeline_model_parallel: + self.models[i].cuda() + self.models[i].prepare_for_inference_(self.cfg) + # # Quantize + # self.models[i] = torch.quantization.quantize_dynamic( + # self.models[i], {torch.nn.Linear}, dtype=torch.qint8 + # ) + # # Torchscript + # self.models[i] = torch.jit.script(self.models[i]) + + # Initialize generator + self.generator = self.task.build_generator(self.models, self.cfg.generation) + + # Handle tokenization and BPE + self.tokenizer = self.task.build_tokenizer(self.cfg.tokenizer) + self.bpe = self.task.build_bpe(self.cfg.bpe) + + # Load alignment dictionary for unknown word replacement + # (None if no unknown word replacement, empty if no path to align dictionary) + self.align_dict = utils.load_align_dict(self.cfg.generation.replace_unk) + + self.max_positions = utils.resolve_max_positions( + self.task.max_positions(), *[model.max_positions() for model in self.models] + ) + + def encode_fn(self, x): + if self.tokenizer is not None: + x = self.tokenizer.encode(x) + if self.bpe is not None: + x = self.bpe.encode(x) + return x + + def decode_fn(self, x): + if self.bpe is not None: + x = self.bpe.decode(x) + if self.tokenizer is not None: + x = self.tokenizer.decode(x) + return x + + def translate(self, inputs, nbest=1): + + start_id = 0 + # for inputs in buffered_read(self.cfg.interactive.input, self.cfg.interactive.buffer_size): + + results = [] + for batch in make_batches(inputs, self.cfg, self.task, self.max_positions, self.encode_fn): + bsz = batch.src_tokens.size(0) + src_tokens = batch.src_tokens + src_lengths = batch.src_lengths + constraints = batch.constraints + if self.use_cuda: + src_tokens = src_tokens.cuda() + src_lengths = src_lengths.cuda() + if constraints is not None: + constraints = constraints.cuda() + + sample = { + "net_input": { + "src_tokens": src_tokens, + "src_lengths": src_lengths, + }, + } + + translate_start_time = time.time() + translations = self.task.inference_step( + self.generator, self.models, sample, constraints=constraints + ) + translate_time = time.time() - translate_start_time + self.total_translate_time += translate_time + list_constraints = [[] for _ in range(bsz)] + if self.cfg.generation.constraints: + list_constraints = [unpack_constraints(c) for c in constraints] + for i, (id, hypos) in enumerate(zip(batch.ids.tolist(), translations)): + src_tokens_i = utils.strip_pad(src_tokens[i], self.tgt_dict.pad()) + constraints = list_constraints[i] + results.append( + ( + start_id + id, + src_tokens_i, + hypos, + { + "constraints": constraints, + "time": translate_time / len(translations), + }, + ) + ) + + # sort output to match input order + result_str = "" + for id_, src_tokens, hypos, info in sorted(results, key=lambda x: x[0]): + + src_str = "" + if self.src_dict is not None: + src_str = self.src_dict.string(src_tokens, self.cfg.common_eval.post_process) + + + # print("S-{}\t{}".format(id_, src_str)) + result_str += "S-{}\t{}".format(id_, src_str) + '\n' + + # print("W-{}\t{:.3f}\tseconds".format(id_, info["time"])) + result_str += "W-{}\t{:.3f}\tseconds".format(id_, info["time"]) + '\n' + + for constraint in info["constraints"]: + # print( + # "C-{}\t{}".format( + # id_, + # self.tgt_dict.string(constraint, self.cfg.common_eval.post_process), + # ) + # ) + result_str += "C-{}\t{}".format( + id_, + self.tgt_dict.string(constraint, self.cfg.common_eval.post_process), + ) + '\n' + + # Process top predictions + for hypo in hypos[: min(len(hypos), nbest)]: + hypo_tokens, hypo_str, alignment = utils.post_process_prediction( + hypo_tokens=hypo["tokens"].int().cpu(), + src_str=src_str, + alignment=hypo["alignment"], + align_dict=self.align_dict, + tgt_dict=self.tgt_dict, + remove_bpe=self.cfg.common_eval.post_process, + extra_symbols_to_ignore=get_symbols_to_strip_from_output(self.generator), + ) + detok_hypo_str = self.decode_fn(hypo_str) + score = hypo["score"] / math.log(2) # convert to base 2 + # original hypothesis (after tokenization and BPE) + # print("H-{}\t{}\t{}".format(id_, score, hypo_str)) + result_str += "H-{}\t{}\t{}".format(id_, score, hypo_str) + '\n' + + # detokenized hypothesis + # print("D-{}\t{}\t{}".format(id_, score, detok_hypo_str)) + result_str += "D-{}\t{}\t{}".format(id_, score, detok_hypo_str) + '\n' + + # print( + # "P-{}\t{}".format( + # id_, + # " ".join( + # map( + # lambda x: "{:.4f}".format(x), + # # convert from base e to base 2 + # hypo["positional_scores"].div_(math.log(2)).tolist(), + # ) + # ), + # ) + # ) + result_str += "P-{}\t{}".format( + id_, + " ".join( + map( + lambda x: "{:.4f}".format(x), + # convert from base e to base 2 + hypo["positional_scores"].div_(math.log(2)).tolist(), + ) + ), + ) + '\n' + + if self.cfg.generation.print_alignment: + alignment_str = " ".join( + ["{}-{}".format(src, tgt) for src, tgt in alignment] + ) + # print("A-{}\t{}".format(id_, alignment_str)) + result_str += "A-{}\t{}".format(id_, alignment_str) + '\n' + + # # update running id_ counter + # start_id += len(inputs) + return result_str diff --git a/app/ai4bharat/transliteration/transformer/en2indic.py b/app/ai4bharat/transliteration/transformer/en2indic.py new file mode 100644 index 0000000000000000000000000000000000000000..baf19bf805ab759a01870d0b0551e74550d72e0f --- /dev/null +++ b/app/ai4bharat/transliteration/transformer/en2indic.py @@ -0,0 +1,112 @@ +import os +from collections.abc import Iterable + +import logging +logging.basicConfig(level=logging.WARNING) + +from .base_engine import BaseEngineTransformer, LANG_LIST_FILE + +F_DIR = os.path.dirname(os.path.realpath(__file__)) + +MODEL_DOWNLOAD_URL = 'https://github.com/AI4Bharat/IndicXlit/releases/download/v1.0/indicxlit-en-indic-v1.0.zip' +DICTS_DOWNLOAD_URL = 'https://github.com/AI4Bharat/IndicXlit/releases/download/v1.0/word_prob_dicts.zip' +XLIT_VERSION = "v1.0" # If model/dict is changed on the storage, do not forget to change this variable in-order to force-download new assets + +def is_folder_writable(folder): + try: + os.makedirs(folder, exist_ok=True) + tmp_file = os.path.join(folder, '.write_test') + with open(tmp_file, 'w') as f: + f.write('Permission Check') + os.remove(tmp_file) + return True + except: + return False + +def is_directory_writable(path): + if os.name == 'nt': + return is_folder_writable(path) + return os.access(path, os.W_OK | os.X_OK) + +class XlitEngineTransformer_En2Indic(BaseEngineTransformer): + """ + For Managing the top level tasks and applications of transliteration + + TODO: Ability to pass `beam_width` dynamically + """ + def __init__(self, lang2use = "all", beam_width=4, rescore=True): + + if is_directory_writable(F_DIR): + models_path = os.path.join(F_DIR, 'models') + else: + user_home = os.path.expanduser("~") + models_path = os.path.join(user_home, '.AI4Bharat_Xlit_Models') + models_path = os.path.join(models_path, "en2indic", XLIT_VERSION) + os.makedirs(models_path, exist_ok=True) + + lang_list_file = os.path.join(models_path, LANG_LIST_FILE) + _all_supported_langs = open(lang_list_file).read().strip().split('\n') + self._all_supported_langs = set(_all_supported_langs) + if "en" in self._all_supported_langs: + self._all_supported_langs.remove("en") + + self._tgt_langs = set() + if isinstance(lang2use, str): + if lang2use == "all": + self._tgt_langs = self._all_supported_langs + elif lang2use in self._all_supported_langs: + self._tgt_langs.add(lang2use) + else: + raise Exception("XlitError: The entered Langauge code not found. Available are {}".format(self._all_supported_langs) ) + elif isinstance(lang2use, Iterable): + for l in lang2use: + if l in self._all_supported_langs: + self._tgt_langs.add(l) + else: + print("XlitError: Language code {} not found, Skipping...".format(l)) + else: + raise Exception("XlitError: lang2use must be a list of language codes (or) string of single language code" ) + + + + model_file_path = self.download_models(models_path, MODEL_DOWNLOAD_URL) + if rescore: + dicts_folder = self.download_dicts(models_path, DICTS_DOWNLOAD_URL) + else: + dicts_folder = None + + super().__init__(models_path, beam_width=beam_width, rescore=rescore) + + @property + def all_supported_langs(self): + return self._all_supported_langs + + @property + def tgt_langs(self): + return self._tgt_langs + + def translit_word(self, word, lang_code="default", topk=4, transliterate_numerals=False): + + if lang_code in self.tgt_langs: + transliterated_word_list = self._transliterate_word(word, src_lang='en', tgt_lang=lang_code, topk=topk, nativize_numerals=transliterate_numerals) + return transliterated_word_list + elif lang_code == "default": + res_dict = {} + for la in self.tgt_langs: + transliterated_word_list = self._transliterate_word(word, src_lang='en', tgt_lang=la, topk=topk, nativize_numerals=transliterate_numerals) + res_dict[la] = transliterated_word_list + return res_dict + else: + raise NotImplementedError("Unsupported lang_code: " + lang_code) + + def translit_sentence(self, eng_sentence, lang_code="default", transliterate_numerals=True): + + if lang_code in self.tgt_langs: + return self._transliterate_sentence(eng_sentence, src_lang='en', tgt_lang=lang_code, nativize_numerals=transliterate_numerals) + elif lang_code == "default": + res_dict = {} + for la in self.tgt_langs: + res_dict[la] = self._transliterate_sentence(eng_sentence, src_lang='en', tgt_lang=la, nativize_numerals=transliterate_numerals) + return res_dict + else: + raise NotImplementedError("Unsupported lang_code: " + lang_code) diff --git a/app/ai4bharat/transliteration/transformer/indic2en.py b/app/ai4bharat/transliteration/transformer/indic2en.py new file mode 100644 index 0000000000000000000000000000000000000000..8d162a0bc92d23ea0f8de0b18388fe32f3be3981 --- /dev/null +++ b/app/ai4bharat/transliteration/transformer/indic2en.py @@ -0,0 +1,78 @@ +import os +from collections.abc import Iterable + +import logging +logging.basicConfig(level=logging.WARNING) + +from .base_engine import BaseEngineTransformer, LANG_LIST_FILE + +F_DIR = os.path.dirname(os.path.realpath(__file__)) + +MODEL_DOWNLOAD_URL = 'https://github.com/AI4Bharat/IndicXlit/releases/download/v1.0/indicxlit-indic-en-v1.0.zip' +DICTS_DOWNLOAD_URL = 'https://github.com/AI4Bharat/IndicXlit/releases/download/v1.0/word_prob_dicts_en.zip' +XLIT_VERSION = "v1.0" # If model/dict is changed on the storage, do not forget to change this variable in-order to force-download new assets + +def is_folder_writable(folder): + try: + os.makedirs(folder, exist_ok=True) + tmp_file = os.path.join(folder, '.write_test') + with open(tmp_file, 'w') as f: + f.write('Permission Check') + os.remove(tmp_file) + return True + except: + return False + +def is_directory_writable(path): + if os.name == 'nt': + return is_folder_writable(path) + return os.access(path, os.W_OK | os.X_OK) + +class XlitEngineTransformer_Indic2En(BaseEngineTransformer): + """ + For Managing the top level tasks and applications of transliteration + + TODO: Ability to pass `beam_width` dynamically + """ + def __init__(self, beam_width=4, rescore=True): + if is_directory_writable(F_DIR): + models_path = os.path.join(F_DIR, 'models') + else: + user_home = os.path.expanduser("~") + models_path = os.path.join(user_home, '.AI4Bharat_Xlit_Models') + models_path = os.path.join(models_path, "indic2en", XLIT_VERSION) + os.makedirs(models_path, exist_ok=True) + + lang_list_file = os.path.join(models_path, LANG_LIST_FILE) + _all_supported_langs = open(lang_list_file).read().strip().split('\n') + self._all_supported_langs = set(_all_supported_langs) + if "en" in self._all_supported_langs: + self._all_supported_langs.remove("en") + + self._tgt_langs = set(["en"]) + + model_file_path = self.download_models(models_path, MODEL_DOWNLOAD_URL) + if rescore: + dicts_folder = self.download_dicts(models_path, DICTS_DOWNLOAD_URL) + else: + dicts_folder = None + + super().__init__(models_path, beam_width=beam_width, rescore=rescore) + + @property + def all_supported_langs(self): + return self._all_supported_langs + + @property + def tgt_langs(self): + return self._tgt_langs + + def translit_word(self, word, lang_code, topk=4): + if lang_code not in self.all_supported_langs: + raise NotImplementedError(f"Language: `{lang_code}` not yet supported") + return self._transliterate_word(word, src_lang=lang_code, tgt_lang='en', topk=topk) + + def translit_sentence(self, indic_sentence, lang_code): + if lang_code not in self.all_supported_langs: + raise NotImplementedError(f"Language: `{lang_code}` not yet supported") + return self._transliterate_sentence(indic_sentence, src_lang=lang_code, tgt_lang='en') diff --git a/app/ai4bharat/transliteration/transformer/models/.gitignore b/app/ai4bharat/transliteration/transformer/models/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..7068cde4d17e9f6c8158b5bf818f296d7fefcaa1 --- /dev/null +++ b/app/ai4bharat/transliteration/transformer/models/.gitignore @@ -0,0 +1 @@ +/**/ \ No newline at end of file diff --git a/app/ai4bharat/transliteration/transformer/models/README.md b/app/ai4bharat/transliteration/transformer/models/README.md new file mode 100644 index 0000000000000000000000000000000000000000..800b4c9e523e7dc8b410ed83a579d4089f846c4a --- /dev/null +++ b/app/ai4bharat/transliteration/transformer/models/README.md @@ -0,0 +1,5 @@ +## Application Binaries + +:warning: Directories inside this folder will not be commited. + +Folder for storing the binaries, executables and weight specific scripts and models diff --git a/app/ai4bharat/transliteration/utils.py b/app/ai4bharat/transliteration/utils.py new file mode 100644 index 0000000000000000000000000000000000000000..416a2cf1d71f790f10f96d6d65701f99cad70a5a --- /dev/null +++ b/app/ai4bharat/transliteration/utils.py @@ -0,0 +1,286 @@ +import re + +LANG_CODE_TO_DISPLAY_NAME = { + # Indo-Aryan + ## Indic-scripts + 'as' : "Assamese - অসমীয়া", + 'bn' : "Bangla - বাংলা", + 'doi': "Dogri - डोगरी", + 'gom': "Goan Konkani - कोंकणी", + 'gu' : "Gujarati - ગુજરાતી", + 'hi' : "Hindi - हिंदी", + 'mai': "Maithili - मैथिली", + 'mr' : "Marathi - मराठी", + 'ne' : "Nepali - नेपाली", + 'or' : "Oriya - ଓଡ଼ିଆ", + 'pa' : "Panjabi - ਪੰਜਾਬੀ", + 'sa' : "Sanskrit - संस्कृतम्", + 'si' : "Sinhala - සිංහල", + ## Perso-Arabic scripts + 'ks' : "Kashmiri - كٲشُر", + 'pnb': "Panjabi (Western) - پن٘جابی", + 'sd' : "Sindhi - سنڌي", + 'skr': "Saraiki - سرائیکی", + 'ur' : "Urdu - اُردُو", + ## Misc + 'dv' : "Dhivehi - ދިވެހި", + + # Dravidian + 'kn' : "Kannada - ಕನ್ನಡ", + 'ml' : "Malayalam - മലയാളം", + 'ta' : "Tamil - தமிழ்", + 'te' : "Telugu - తెలుగు", + + # Tibeto-Burman + 'brx': "Boro - बड़ो", + 'mni': "Manipuri - ꯃꯤꯇꯩꯂꯣꯟ", + + # Munda + 'sat': "Santali - ᱥᱟᱱᱛᱟᱲᱤ", + + # Misc + 'en' : "English", +} + +PERSOARABIC_LANG_CODES = { + 'ks', + 'pnb', + 'sd', + 'skr', + 'ur', +} + +RTL_LANG_CODES = set(PERSOARABIC_LANG_CODES) +RTL_LANG_CODES.add('dv') + +# Default/Official language to script mapping +LANG_CODE_TO_SCRIPT_CODE = { + + # Indo-Aryan + "as" : "Beng", + "bn" : "Beng", + "doi" : "Deva", + "dv" : "Thaa", + "gom" : "Deva", + "gu" : "Gujr", + "hi" : "Deva", + "ks" : "Aran", + "mai" : "Deva", + "mr" : "Deva", + "ne" : "Deva", + "or" : "Orya", + "pa" : "Guru", + "pnb" : "Aran", + "sa" : "Deva", + "sd" : "Arab", + "si" : "Sinh", + "skr" : "Aran", + "ur" : "Aran", + + # Dravidian + "kn" : "Knda", + "ml" : "Mlym", + "ta" : "Taml", + "te" : "Telu", + + # Tibeto-Burman + "brx" : "Deva", + "mni" : "Mtei", + + # Munda + "sat" : "Olck", + + # Misc + "en" : "Latn", +} + +SCRIPT_CODE_TO_UNICODE_CHARS_RANGE_STR = { + # ISO 15924 codes for script names + + # North Indic + "Beng": "\u0980-\u09FF", + "Deva": "\u0900-\u097F", + "Gujr": "\u0A80-\u0AFF", + "Guru": "\u0A00-\u0A7F", + "Orya": "\u0B00-\u0B7F", + + # South Indic + "Knda": "\u0C80-\u0CFF", + "Mlym": "\u0D00-\u0D7F", + "Sinh": "\u0D80-\u0DFF", + "Taml": "\u0B80-\u0BFF", + "Telu": "\u0C00-\u0C7F", + + # Tibetic + "Mtei": "\uABC0-\uABFF", + + # Misc + "Arab": "\u0600-\u06FF\u0750-\u077F\u0870-\u089F\u08A0-\u08FF", # Perso-Arabic + "Aran": "\u0600-\u06FF\u0750-\u077F\u0870-\u089F\u08A0-\u08FF", # Perso-Arabic (Nastaliq code) + "Latn": "\u0041-\u005A\u0061-\u007A", # includes only basic/unaccented Roman + "Olck": "\u1C50-\u1C7F", + "Thaa": "\u0780-\u07BF", +} + +GOOGLE_FONTS = { + "gom": "Tiro Devanagari Marathi", + "ks" : "Noto Nastaliq Urdu", + "mni": "Noto Sans Meetei Mayek", + "mr" : "Tiro Devanagari Marathi", + "sa" : "Tiro Devanagari Sanskrit", + "sat": "Noto Sans Ol Chiki", + "sd" : "Lateef", + "ur" : "Noto Nastaliq Urdu", +} + +FALLBACK_FONTS = { + "gom": "serif", + "ks" : "serif", + "mni": "sans-serif", + "mr" : "serif", + "sa" : "serif", + "sat": "sans-serif", + "sd" : "serif", + "ur" : "serif", +} + +INDIC_TO_LATIN_PUNCT = { + ## List of all punctuations across languages + + # Brahmic + '।': '.', # Nagari + ## Archaic Indic + '॥': "..", # Sanskrit + '෴': '.', # Sinhala + ## Meetei (influenced from Burmese) + '꫰': ',', + '꯫': '.', + + # Ol Chiki + '᱾': '.', + '᱿': '..', + + # Arabic + '۔': '.', + '؟': '?', + '،': ',', + '؛': ';', + '۝': "..", +} + +INDIC_TO_LATIN_PUNCT_TRANSLATOR = str.maketrans(INDIC_TO_LATIN_PUNCT) + +NON_LATIN_FULLSTOP_LANGS = { + # Brahmic + 'as' : '।', + 'bn' : '।', + 'brx': '।', + 'doi': '।', + 'hi' : '।', + 'mai': '।', + 'mni': '꯫', + 'ne' : '।', + 'or' : '।', + 'pa' : '।', + 'sa' : '।', + 'sat': '᱾', + + # Nastaliq + 'ks' : '۔', + 'pnb': '۔', + # 'sd' : '۔', # Sindhi uses Naskh, hence use latin + 'skr': '۔', + 'ur' : '۔', +} + +ENDS_WITH_LATIN_FULLSTOP_REGEX = re.compile("(^|.*[^.])\.$") + +def nativize_latin_fullstop(text, lang_code): + if lang_code in NON_LATIN_FULLSTOP_LANGS and ENDS_WITH_LATIN_FULLSTOP_REGEX.match(text): + return text[:-1] + NON_LATIN_FULLSTOP_LANGS[lang_code] + return text + +LATIN_TO_PERSOARABIC_PUNCTUATIONS = { + # Except full-stop (since period-mark is ambiguous in usage, like fullforms) + '?': '؟', + ',': '،', + ';': '؛', +} + +LATIN_TO_PERSOARABIC_PUNC_TRANSLATOR = str.maketrans(LATIN_TO_PERSOARABIC_PUNCTUATIONS) + +SCRIPT_CODE_TO_NUMERALS = { + # ISO 15924 codes for script names + + # North Indic + "Beng": "০১২৩৪৫৬৭৮৯", + "Deva": "०१२३४५६७८९", + "Gujr": "૦૧૨૩૪૫૬૭૮૯", + "Guru": "੦੧੨੩੪੫੬੭੮੯", + "Orya": "୦୧୨୩୪୫୬୭୮୯", + + # South Indic + "Knda": "೦೧೨೩೪೫೬೭೮೯", + "Mlym": "൦൧൨൩൪൫൬൭൮൯", + "Sinh": "෦෧෨෩෪෫෬෭෮෯", + "Taml": "௦௧௨௩௪௫௬௭௮௯", + "Telu": "౦౧౨౩౪౫౬౭౮౯", + + # Tibetic + "Mtei": "꯰꯱꯲꯳꯴꯵꯶꯷꯸꯹", + + # Misc + "Arab": "۰۱۲۳۴۵۶۷۸۹", # Perso-Arabic numerals + "Aran": "۰۱۲۳۴۵۶۷۸۹", # Perso-Arabic numerals + "Latn": "0123456789", + "Olck": "᱐᱑᱒᱓᱔᱕᱖᱗᱘᱙", + "Thaa": "٠١٢٣٤٥٦٧٨٩", # East-Arabic numerals. (Dhivehi does code-mixing with Arabic) +} + +LANG_CODE_TO_NUMERALS = { + lang_code: SCRIPT_CODE_TO_NUMERALS[script_code] + for lang_code, script_code in LANG_CODE_TO_SCRIPT_CODE.items() +} + +INDIC_TO_STANDARD_NUMERALS_GLOBAL_MAP = {} +for lang_code, lang_numerals in LANG_CODE_TO_NUMERALS.items(): + map_dict = {lang_numeral: en_numeral for lang_numeral, en_numeral in zip(lang_numerals, LANG_CODE_TO_NUMERALS["en"])} + INDIC_TO_STANDARD_NUMERALS_GLOBAL_MAP.update(map_dict) + +INDIC_TO_STANDARD_NUMERALS_TRANSLATOR = str.maketrans(INDIC_TO_STANDARD_NUMERALS_GLOBAL_MAP) + +NATIVE_TO_LATIN_NUMERALS_TRANSLATORS = { + lang_code: str.maketrans({lang_numeral: en_numeral for lang_numeral, en_numeral in zip(lang_numerals, LANG_CODE_TO_NUMERALS["en"])}) + for lang_code, lang_numerals in LANG_CODE_TO_NUMERALS.items() + if lang_code != "en" +} + +LATIN_TO_NATIVE_NUMERALS_TRANSLATORS = { + lang_code: str.maketrans({en_numeral: lang_numeral for en_numeral, lang_numeral in zip(LANG_CODE_TO_NUMERALS["en"], lang_numerals)}) + for lang_code, lang_numerals in LANG_CODE_TO_NUMERALS.items() + if lang_code != "en" +} + +WORDFINAL_INDIC_VIRAMA_REGEX = re.compile("(\u09cd|\u094d|\u0acd|\u0a4d|\u0b4d|\u0ccd|\u0d4d|\u0dca|\u0bcd|\u0c4d|\uaaf6)$") +def hardfix_wordfinal_virama(word): + # Add ZWNJ after a word-final halanta + # Not applicable for non-Brahmic scripts (like Arabic & Ol-Chiki) + return WORDFINAL_INDIC_VIRAMA_REGEX.sub("\\1\u200c", word) + +ODIA_CONFUSING_YUKTAKSHARA_REGEX = re.compile("(\u0b4d)(ବ|ଵ|ୱ|ଯ|ୟ)") +def fix_odia_confusing_ambiguous_yuktakshara(word): + # Add ZWNJ in-between to force-render virama in conjunct + return ODIA_CONFUSING_YUKTAKSHARA_REGEX.sub("\\1\u200c\\2", word) + +LATIN_WORDFINAL_CONSONANTS_CHECKER_REGEX = re.compile(".*([bcdfghjklmnpqrstvwxyz])$") +DEVANAGARI_WORDFINAL_CONSONANTS_REGEX = re.compile("([\u0915-\u0939\u0958-\u095f\u0979-\u097c\u097e-\u097f])$") +def explicit_devanagari_wordfinal_schwa_delete(roman_word, indic_word): + if LATIN_WORDFINAL_CONSONANTS_CHECKER_REGEX.match(roman_word): + indic_word = DEVANAGARI_WORDFINAL_CONSONANTS_REGEX.sub("\\1\u094d", indic_word) + return indic_word + +# To replace last N occurences of a substring in a string +# Src: https://stackoverflow.com/questions/2556108/ +def rreplace(text, find_pattern, replace_pattern, match_count=1): + splits = text.rsplit(find_pattern, match_count) + return replace_pattern.join(splits) diff --git a/app/ai4bharat/transliteration/xlit_server.py b/app/ai4bharat/transliteration/xlit_server.py new file mode 100644 index 0000000000000000000000000000000000000000..12e5c004027d1b28ed74695d9559f7c6c28533ef --- /dev/null +++ b/app/ai4bharat/transliteration/xlit_server.py @@ -0,0 +1,207 @@ +""" +Expose Transliteration Engine as an HTTP API. + +USAGE: +``` +from ai4bharat.transliteration import xlit_server +app, engine = xlit_server.get_app() +app.run(host='0.0.0.0', port=8000) +``` +Sample URLs: + http://localhost:8000/tl/ta/amma + http://localhost:8000/languages + +FORMAT: + Based on the Varnam API standard + https://api.varnamproject.com/tl/hi/bharat +""" + +from flask import Flask, jsonify, request, make_response +from flask_limiter import Limiter +from uuid import uuid4 +from datetime import datetime +import traceback +import enum + +from .utils import LANG_CODE_TO_DISPLAY_NAME, RTL_LANG_CODES, LANG_CODE_TO_SCRIPT_CODE, GOOGLE_FONTS, FALLBACK_FONTS + +class XlitError(enum.Enum): + lang_err = "Unsupported langauge ID requested ;( Please check available languages." + string_err = "String passed is incompatable ;(" + internal_err = "Internal crash ;(" + unknown_err = "Unknown Failure" + loading_err = "Loading failed ;( Check if metadata/paths are correctly configured." + +def get_remote_address() -> str: + return request.headers.get('X-Forwarded-For', request.remote_addr) or "127.0.0.1" + +app = Flask(__name__) +app.config['JSON_AS_ASCII'] = False +limiter = Limiter( + get_remote_address, + app=app, + storage_uri="memory://", +) + +## ----------------------------- Xlit Engine -------------------------------- ## + +from .xlit_src import XlitEngine + +MAX_SUGGESTIONS = 8 +DEFAULT_NUM_SUGGESTIONS = 5 + +ENGINE = { + "en2indic": XlitEngine(beam_width=MAX_SUGGESTIONS, rescore=True, model_type="transformer", src_script_type = "roman"), + "indic2en": XlitEngine(beam_width=MAX_SUGGESTIONS, rescore=False, model_type="transformer", src_script_type = "indic"), +} + +EXPOSED_LANGS = [ + { + "LangCode": lang_code, # ISO-639 code + "Identifier": lang_code, # ISO-639 code + "DisplayName": LANG_CODE_TO_DISPLAY_NAME[lang_code], + "Author": "AI4Bharat", # Name of developer / team + "CompiledDate": "09-April-2022", # date on which model was trained + "IsStable": True, # Set `False` if the model is experimental + "Direction": "rtl" if lang_code in RTL_LANG_CODES else "ltr", + "ScriptCode": LANG_CODE_TO_SCRIPT_CODE[lang_code], + "GoogleFont": GOOGLE_FONTS[lang_code] if lang_code in GOOGLE_FONTS else None, + "FallbackFont": FALLBACK_FONTS[lang_code] if lang_code in FALLBACK_FONTS else None, + } for lang_code in sorted(ENGINE["en2indic"].all_supported_langs) +] + +def get_app(): + return app, ENGINE + +## ---------------------------- API End-points ------------------------------ ## + +@app.route('/languages', methods = ['GET', 'POST']) +def supported_languages(): + # Format - https://xlit-api.ai4bharat.org/languages + response = make_response(jsonify(EXPOSED_LANGS)) + if 'xlit_user_id' not in request.cookies: + # host = request.environ['HTTP_ORIGIN'].split('://')[1] + host = '.ai4bharat.org' + response.set_cookie('xlit_user_id', uuid4().hex, max_age=365*24*60*60, domain=host, samesite='None', secure=True, httponly=True) + return response + +@app.route('/tl//', methods = ['GET']) +@limiter.limit("5/second") +def xlit_api(lang_code, eng_word): + # Format: https://xlit-api.ai4bharat.org/tl/ta/bharat + response = { + 'success': False, + 'error': '', + 'at': str(datetime.utcnow()) + ' +0000 UTC', + 'input': eng_word.strip(), + 'result': '' + } + + transliterate_numerals = request.args.get('transliterate_numerals', default=False, type=lambda v: v.lower() == 'true') + num_suggestions = request.args.get('num_suggestions', default=DEFAULT_NUM_SUGGESTIONS, type=int) + + if lang_code not in ENGINE["en2indic"].all_supported_langs: + response['error'] = 'Invalid scheme identifier. Supported languages are: '+ str(ENGINE["en2indic"].all_supported_langs) + return jsonify(response) + + try: + ## Limit char count to --> 70 + xlit_result = ENGINE["en2indic"].translit_word(eng_word[:70], lang_code, topk=num_suggestions, transliterate_numerals=transliterate_numerals) + except Exception as e: + xlit_result = XlitError.internal_err + + + if isinstance(xlit_result, XlitError): + response['error'] = xlit_result.value + print("XlitError:", traceback.format_exc()) + else: + response['result'] = xlit_result + response['success'] = True + + return jsonify(response) + +@app.route('/rtl//', methods = ['GET']) +@limiter.limit("5/second") +def reverse_xlit_api(lang_code, word): + # Format: https://api.varnamproject.com/rtl/hi/भारत + response = { + 'success': False, + 'error': '', + 'at': str(datetime.utcnow()) + ' +0000 UTC', + 'input': word.strip(), + 'result': '' + } + + if lang_code not in ENGINE["indic2en"].all_supported_langs: + response['error'] = 'Invalid scheme identifier. Supported languages are: '+ str(ENGINE["indic2en"].all_supported_langs) + return jsonify(response) + + num_suggestions = request.args.get('num_suggestions', default=DEFAULT_NUM_SUGGESTIONS, type=int) + + try: + ## Limit char count to --> 70 + xlit_result = ENGINE["indic2en"].translit_word(word[:70], lang_code, topk=num_suggestions) + except Exception as e: + xlit_result = XlitError.internal_err + + if isinstance(xlit_result, XlitError): + response['error'] = xlit_result.value + print("XlitError:", traceback.format_exc()) + else: + response['result'] = xlit_result + response['success'] = True + + return jsonify(response) + +@app.route('/transliterate', methods=['POST']) +@limiter.limit("5/second") +def ulca_api(): + ''' + ULCA-compliant endpoint. See for sample request-response: + https://github.com/ULCA-IN/ulca/tree/master/specs/examples/model/transliteration-model + ''' + data = request.get_json(force=True) + + if "input" not in data or "config" not in data: + return jsonify({ + "status": { + "statusCode": 400, + "message": "Ensure `input` and `config` fields missing." + } + }), 400 + + if (data["config"]["language"]["sourceLanguage"] == "en" and data["config"]["language"]["targetLanguage"] in ENGINE["en2indic"].all_supported_langs) or (data["config"]["language"]["sourceLanguage"] in ENGINE["indic2en"].all_supported_langs and data["config"]["language"]["targetLanguage"] == 'en'): + pass + else: + return jsonify({ + "status": { + "statusCode": 501, + "message": "The mentioned language-pair is not supported yet." + } + }), 501 + + is_sentence = data["config"]["isSentence"] if "isSentence" in data["config"] else False + num_suggestions = 1 if is_sentence else (data["config"]["numSuggestions"] if "numSuggestions" in data["config"] else 5) + + if data["config"]["language"]["targetLanguage"] == "en": + engine = ENGINE["indic2en"] + lang_code = data["config"]["language"]["sourceLanguage"] + else: + engine = ENGINE["en2indic"] + lang_code = data["config"]["language"]["targetLanguage"] + + outputs = [] + for item in data["input"]: + if is_sentence: + item["target"] = [engine.translit_sentence(item["source"], lang_code=lang_code)] + else: + item["source"] = item["source"][:32] + item["target"] = engine.translit_word(item["source"], lang_code=lang_code, topk=num_suggestions) + + return { + "output": data["input"], + # "status": { + # "statusCode": 200, + # "message" : "success" + # } + }, 200 diff --git a/app/ai4bharat/transliteration/xlit_src.py b/app/ai4bharat/transliteration/xlit_src.py new file mode 100644 index 0000000000000000000000000000000000000000..9ca2be61fd7e578b1d70cb565d52d0160ecdc15f --- /dev/null +++ b/app/ai4bharat/transliteration/xlit_src.py @@ -0,0 +1,19 @@ +def XlitEngine( + lang2use = "all", beam_width=4, rescore=True, + model_type = "transformer", + src_script_type = "roman", +): + if model_type == "transformer": + if src_script_type in {"roman", "latin", "en"}: + from .transformer import XlitEngineTransformer_En2Indic + return XlitEngineTransformer_En2Indic(lang2use, beam_width=beam_width, rescore=rescore) + elif src_script_type == "indic": + from .transformer import XlitEngineTransformer_Indic2En + return XlitEngineTransformer_Indic2En(beam_width=beam_width, rescore=rescore) + + elif model_type == "rnn": + assert src_script_type in {"roman", "latin", "en"} + from .rnn.engine import XlitEngineRNN + return XlitEngineRNN(lang2use, beam_width=beam_width, rescore=rescore) + + raise NotImplementedError() diff --git a/dependencies.txt b/dependencies.txt new file mode 100644 index 0000000000000000000000000000000000000000..e4d0843346cba2f82ad6602593c3354a00a5dcd5 --- /dev/null +++ b/dependencies.txt @@ -0,0 +1,16 @@ +pydload +flask +flask_cors +Flask-Limiter +gevent +sacremoses +pandas +tqdm +ujson +mock +tensorboardX +pyarrow +fairseq + +urduhack +indic_nlp_library diff --git a/models/en2indic/corpus-bin/dict.as.txt b/models/en2indic/corpus-bin/dict.as.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.as.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.bn.txt b/models/en2indic/corpus-bin/dict.bn.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.bn.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.brx.txt b/models/en2indic/corpus-bin/dict.brx.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.brx.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.en.txt b/models/en2indic/corpus-bin/dict.en.txt new file mode 100644 index 0000000000000000000000000000000000000000..1ea850555b51a8c4039207fb5f05fb699c413713 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.en.txt @@ -0,0 +1,28 @@ +a 68719571 +i 22459538 +n 20241343 +h 19145187 +t 16984308 +r 16344076 +u 15284650 +e 13961033 +k 13141063 +l 12147489 +d 11019484 +s 10468436 +m 10243268 +o 9673748 +y 7666719 +p 7626925 +v 6667573 +g 5815215 +b 4383424 +c 4328378 +j 2062662 +w 1104853 +z 660571 +f 649435 +x 121633 +q 70628 +madeupword0000 0 +madeupword0001 0 diff --git a/models/en2indic/corpus-bin/dict.gom.txt b/models/en2indic/corpus-bin/dict.gom.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.gom.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.gu.txt b/models/en2indic/corpus-bin/dict.gu.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.gu.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.hi.txt b/models/en2indic/corpus-bin/dict.hi.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.hi.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.kn.txt b/models/en2indic/corpus-bin/dict.kn.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.kn.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.ks.txt b/models/en2indic/corpus-bin/dict.ks.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.ks.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.mai.txt b/models/en2indic/corpus-bin/dict.mai.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.mai.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.ml.txt b/models/en2indic/corpus-bin/dict.ml.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.ml.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.mlt.txt b/models/en2indic/corpus-bin/dict.mlt.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.mlt.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.mni.txt b/models/en2indic/corpus-bin/dict.mni.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.mni.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.mr.txt b/models/en2indic/corpus-bin/dict.mr.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.mr.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.ne.txt b/models/en2indic/corpus-bin/dict.ne.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.ne.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.or.txt b/models/en2indic/corpus-bin/dict.or.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.or.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.pa.txt b/models/en2indic/corpus-bin/dict.pa.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.pa.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.sa.txt b/models/en2indic/corpus-bin/dict.sa.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.sa.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.sd.txt b/models/en2indic/corpus-bin/dict.sd.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.sd.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.si.txt b/models/en2indic/corpus-bin/dict.si.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.si.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.ta.txt b/models/en2indic/corpus-bin/dict.ta.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.ta.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.te.txt b/models/en2indic/corpus-bin/dict.te.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.te.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/corpus-bin/dict.ur.txt b/models/en2indic/corpus-bin/dict.ur.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/en2indic/corpus-bin/dict.ur.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/en2indic/model_checkpoint.pt b/models/en2indic/model_checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..b41b0ff81bcca58330de6d2d3e1ac500a1759877 --- /dev/null +++ b/models/en2indic/model_checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f03fe0dfb2edc40f3c11f9293c4feda4fa8ed5366fec2981391606f224a09f7 +size 138135425 diff --git a/models/en2indic/transformer/indicxlit.pt b/models/en2indic/transformer/indicxlit.pt new file mode 100644 index 0000000000000000000000000000000000000000..b41b0ff81bcca58330de6d2d3e1ac500a1759877 --- /dev/null +++ b/models/en2indic/transformer/indicxlit.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f03fe0dfb2edc40f3c11f9293c4feda4fa8ed5366fec2981391606f224a09f7 +size 138135425 diff --git a/models/indic2en/corpus-bin/dict.as.txt b/models/indic2en/corpus-bin/dict.as.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.as.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.bn.txt b/models/indic2en/corpus-bin/dict.bn.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.bn.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.brx.txt b/models/indic2en/corpus-bin/dict.brx.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.brx.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.en.txt b/models/indic2en/corpus-bin/dict.en.txt new file mode 100644 index 0000000000000000000000000000000000000000..1ea850555b51a8c4039207fb5f05fb699c413713 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.en.txt @@ -0,0 +1,28 @@ +a 68719571 +i 22459538 +n 20241343 +h 19145187 +t 16984308 +r 16344076 +u 15284650 +e 13961033 +k 13141063 +l 12147489 +d 11019484 +s 10468436 +m 10243268 +o 9673748 +y 7666719 +p 7626925 +v 6667573 +g 5815215 +b 4383424 +c 4328378 +j 2062662 +w 1104853 +z 660571 +f 649435 +x 121633 +q 70628 +madeupword0000 0 +madeupword0001 0 diff --git a/models/indic2en/corpus-bin/dict.gom.txt b/models/indic2en/corpus-bin/dict.gom.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.gom.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.gu.txt b/models/indic2en/corpus-bin/dict.gu.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.gu.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.hi.txt b/models/indic2en/corpus-bin/dict.hi.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.hi.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.kn.txt b/models/indic2en/corpus-bin/dict.kn.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.kn.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.ks.txt b/models/indic2en/corpus-bin/dict.ks.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.ks.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.mai.txt b/models/indic2en/corpus-bin/dict.mai.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.mai.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.ml.txt b/models/indic2en/corpus-bin/dict.ml.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.ml.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.mlt.txt b/models/indic2en/corpus-bin/dict.mlt.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.mlt.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.mni.txt b/models/indic2en/corpus-bin/dict.mni.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.mni.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.mr.txt b/models/indic2en/corpus-bin/dict.mr.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.mr.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.ne.txt b/models/indic2en/corpus-bin/dict.ne.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.ne.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.or.txt b/models/indic2en/corpus-bin/dict.or.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.or.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.pa.txt b/models/indic2en/corpus-bin/dict.pa.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.pa.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.sa.txt b/models/indic2en/corpus-bin/dict.sa.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.sa.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.sd.txt b/models/indic2en/corpus-bin/dict.sd.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.sd.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.si.txt b/models/indic2en/corpus-bin/dict.si.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.si.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.ta.txt b/models/indic2en/corpus-bin/dict.ta.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.ta.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.te.txt b/models/indic2en/corpus-bin/dict.te.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.te.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/corpus-bin/dict.ur.txt b/models/indic2en/corpus-bin/dict.ur.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ed74d03ca8e10b9af2bd2b8cfec9916908e8394 --- /dev/null +++ b/models/indic2en/corpus-bin/dict.ur.txt @@ -0,0 +1,780 @@ +് 7831906 +ा 7753242 +् 7292980 +் 6337783 +र 5136450 +ി 4077022 +ക 3716219 +ि 3476579 +க 3411613 +ന 3288280 +न 3261805 +್ 3259395 +ു 3250933 +क 3175462 +त 3146118 +स 2934278 +ಿ 2902907 +ാ 2868401 +ி 2806664 +े 2791797 +म 2739459 +ு 2727830 +ത 2681898 +த 2650234 +य 2590723 +్ 2427685 +व 2394855 +ल 2367504 +യ 2252560 +ी 2082290 +प 2039410 +ರ 1974191 +ి 1949182 +ப 1927040 +ದ 1871007 +ா 1862999 +ो 1841699 +ട 1779125 +ु 1775812 +ು 1772547 +ు 1740915 +ಾ 1726413 +ட 1705307 +న 1702819 +ര 1700332 +ా 1649345 +द 1645406 +മ 1589528 +ர 1583020 +ம 1574829 +ല 1554403 +െ 1552303 +പ 1542077 +ं 1500605 +ಗ 1389857 +வ 1380399 +ೆ 1344041 +വ 1338689 +ಲ 1329974 +ನ 1316658 +ర 1313610 +ತ 1306058 +च 1279013 +া 1271787 +ग 1264132 +ల 1252560 +ವ 1252274 +ன 1244601 +ह 1184744 +ಕ 1152519 +ब 1141026 +ல 1125109 +ய 1100872 +క 1091189 +ం 1087823 +ை 1049553 +ണ 1031498 +ള 1018765 +ಸ 1011256 +ം 998025 +ज 995621 +্ 983466 +ા 952612 +র 932990 +റ 931171 +ट 927599 +ಯ 917403 +ள 916994 +ச 913755 +श 911496 +ಂ 905844 +സ 864530 +ప 847746 +త 843409 +ച 829346 +ற 798360 +ি 751180 +వ 742254 +ോ 734064 +ে 719421 +ન 705501 +స 696532 +ध 690620 +્ 680861 +ో 669523 +ا 669102 +ట 663866 +మ 656100 +ड 654655 +भ 651554 +ద 641533 +ే 640736 +ર 636008 +ಳ 633194 +ण 614949 +ಮ 604021 +ू 601591 +ন 594173 +ങ 590456 +േ 583498 +చ 575256 +ی 565327 +డ 561553 +ष 557541 +ক 555215 +ந 542328 +య 540641 +ر 536889 +ಪ 536520 +و 514545 +గ 502444 +ಡ 494180 +ಬ 488662 +ી 465235 +ै 464937 +ே 460790 +ಟ 453706 +ે 449905 +ব 433280 +ল 429346 +স 428714 +ত 422421 +ೇ 413313 +ख 409658 +अ 401097 +ن 399134 +ম 397122 +थ 393868 +ೊ 391283 +ો 387613 +સ 386400 +ோ 377607 +ಹ 373723 +મ 368271 +ண 362504 +ദ 361548 +ெ 357303 +ક 352223 +ু 348806 +ె 338596 +િ 333245 +ં 314034 +প 311464 +ः 309845 +फ 308251 +୍ 297228 +ਾ 295315 +ീ 290090 +વ 289884 +ൂ 288859 +ഷ 285531 +ശ 285162 +લ 281966 +ೋ 276902 +ା 275787 +അ 275186 +ਰ 273401 +ک 269396 +ർ 267939 +দ 261805 +ೂ 261396 +ए 259552 +ل 259290 +ഗ 258127 +ൊ 255585 +ର 253514 +ీ 253098 +م 252411 +য 247695 +ங 246764 +அ 246013 +ृ 244615 +బ 240932 +س 236560 +इ 236254 +उ 233778 +ൽ 233293 +ট 232753 +ழ 232240 +ି 229300 +પ 229281 +ொ 224396 +ુ 223972 +ো 218611 +ટ 214792 +ജ 212908 +ബ 208592 +গ 208088 +ಜ 207170 +ત 204887 +ಚ 204752 +आ 204518 +ധ 201676 +ਸ 199035 +ई 195651 +ય 191927 +ಶ 191447 +ഞ 189838 +ँ 189099 +ഹ 188769 +ూ 186173 +জ 184862 +ੀ 182145 +జ 179015 +ಣ 177731 +ூ 176731 +ഴ 176284 +ഭ 173248 +ौ 169726 +ಅ 168304 +হ 167256 +ீ 164493 +ب 163776 +ী 163711 +د 163087 +ت 162907 +छ 160742 +କ 160587 +ਿ 159881 +ಷ 159876 +ਲ 159560 +ై 156049 +ગ 155144 +இ 154345 +ೀ 154200 +ठ 152317 +শ 151258 +ਕ 150728 +అ 149951 +ડ 147911 +ই 147722 +घ 147573 +બ 145478 +ङ 145100 +ਨ 140231 +ొ 139535 +ୁ 139047 +ہ 138580 +پ 131146 +ळ 130490 +శ 130396 +ൾ 130218 +ಧ 127108 +જ 126568 +ష 126093 +ٹ 124947 +ନ 123701 +દ 123431 +ৰ 122045 +େ 120043 +హ 118295 +চ 117863 +ಭ 116868 +گ 115328 +ੋ 114540 +ൻ 113776 +ਮ 113278 +ভ 111864 +ആ 111033 +ੇ 109242 +શ 106348 +உ 105245 +ବ 104131 +હ 103726 +ഡ 102591 +ਟ 102051 +ञ 100555 +ড 99272 +ధ 97828 +ஸ 97395 +ഇ 96636 +ਪ 96138 +ਵ 93741 +ൈ 93389 +ସ 92089 +় 90911 +ମ 90610 +ج 90375 +થ 88809 +झ 86797 +భ 86210 +ਂ 85691 +ପ 83696 +ೈ 82452 +ش 81742 +எ 81400 +ତ 81377 +ਗ 80351 +ళ 79437 +ধ 78939 +ಆ 78898 +ஆ 78329 +ਜ 77913 +ও 77697 +ھ 77660 +ഥ 77478 +़ 76676 +ز 76333 +ষ 76199 +ഉ 75827 +ف 75535 +ഫ 75340 +ਬ 74672 +എ 74176 +ణ 73432 +ஜ 73423 +ଲ 72784 +ণ 72209 +ચ 71702 +ఆ 69731 +ফ 68649 +ॉ 68601 +ൃ 68477 +ਤ 68342 +ੁ 68315 +એ 67749 +ફ 67301 +ભ 64665 +ഖ 63274 +অ 63129 +ಥ 63089 +ਦ 62427 +ੈ 62208 +ੰ 62025 +ڈ 61851 +ओ 61686 +আ 61016 +਼ 60651 +ਆ 60280 +খ 60040 +ਡ 57122 +ং 56808 +থ 56297 +ਹ 55338 +ढ 55202 +ઓ 54677 +ଙ 53560 +ಫ 53438 +ஷ 53043 +ધ 52644 +ଦ 52558 +ऽ 52482 +ఎ 51926 +ఫ 51574 +ಎ 51555 +چ 50768 +ഒ 50432 +ಉ 49471 +ઇ 49344 +ଗ 49085 +ૂ 48659 +ଟ 48020 +উ 47973 +અ 46936 +ಖ 46466 +ೃ 46113 +ಇ 46089 +ણ 45261 +ي 43659 +এ 43467 +ছ 42906 +థ 41508 +ખ 41469 +ୋ 41085 +ୟ 40769 +ઈ 40062 +ূ 40025 +ఉ 40014 +ୀ 39918 +ଜ 39288 +ஞ 39251 +ળ 39134 +ଡ 39108 +ஒ 38985 +ହ 37986 +ഘ 37390 +ੱ 36553 +ق 35985 +ೌ 35643 +ષ 35625 +ఇ 35570 +ଣ 35520 +੍ 35519 +ଇ 34743 +ਅ 34518 +ॅ 34195 +આ 34194 +ਫ 34187 +ઝ 33567 +ੂ 33143 +ৃ 33004 +ൌ 32485 +ಒ 31408 +ృ 31111 +ଶ 29841 +خ 29611 +ਚ 29600 +ঙ 27816 +ଥ 27300 +ఖ 26315 +ح 26251 +ଆ 25848 +ਈ 25643 +ஹ 25034 +ଚ 24422 +ଭ 24158 +ঞ 24088 +ଳ 23975 +ഓ 23963 +ౌ 23447 +ஏ 23400 +ઉ 23382 +ਇ 23005 +ঘ 21243 +ਖ 21087 +ଷ 21012 +ع 20919 +් 20840 +ਐ 20337 +ৈ 19351 +ಘ 19190 +ഠ 18361 +آ 18332 +ଧ 18302 +ਣ 17835 +ઘ 17460 +ঠ 17426 +ഏ 17344 +ි 16873 +ص 16660 +ৌ 15859 +ଅ 15581 +ৱ 15490 +ව 15277 +ଯ 15173 +ଏ 15111 +න 14867 +ঁ 14554 +ڑ 14537 +ੌ 14490 +ஓ 14130 +ਉ 14096 +ଖ 14054 +ஊ 13996 +ଉ 13707 +ੜ 13673 +ಠ 13611 +ය 13435 +છ 13231 +ਧ 13115 +ૃ 12965 +ਥ 12946 +ఒ 12812 +ਭ 12757 +ఏ 12752 +ଫ 12577 +ා 12471 +ਓ 12297 +ක 12103 +ऊ 12065 +ਯ 11973 +ئ 11819 +غ 11498 +ත 11478 +ఘ 11145 +ൺ 11141 +ୱ 11074 +ଠ 10987 +ઠ 10727 +ں 10641 +ଛ 10633 +ಞ 10630 +ڪ 10586 +ஈ 10342 +ර 10296 +ಏ 9659 +ه 9583 +ૈ 9495 +ਏ 9482 +ු 9300 +औ 9282 +ଂ 8708 +ම 8530 +ස 8384 +ৎ 8187 +ঝ 8096 +ط 7962 +ے 7925 +ऋ 7697 +ऐ 7559 +ظ 7428 +ୂ 7392 +ఊ 7272 +ꯤ 6734 +଼ 6690 +ૌ 6666 +ଞ 6554 +ୃ 6436 +ऑ 6413 +ල 6271 +ਘ 6266 +ද 6176 +ഈ 6147 +ප 6119 +ಓ 6062 +ض 5898 +ఓ 5774 +ٽ 5718 +ꯥ 5715 +ૉ 5671 +ಛ 5643 +ஃ 5629 +ఞ 5600 +ఐ 5540 +ఈ 5420 +َ 5404 +ઢ 5385 +ഊ 5311 +ଁ 5249 +ஐ 5240 +ଘ 5176 +ௌ 5019 +ഐ 4912 +ఠ 4888 +ഛ 4817 +ේ 4790 +ෙ 4747 +ಐ 4622 +ଓ 4596 +ذ 4533 +ට 4334 +ಈ 4294 +ਛ 4239 +ග 4223 +ಢ 4171 +ਊ 4170 +ਝ 3967 +ී 3958 +ث 3939 +ء 3926 +ٕ 3728 +ِ 3665 +හ 3567 +ઞ 3558 +ڙ 3541 +ਠ 3478 +ಊ 3428 +ڻ 3361 +ঃ 3303 +ଝ 3252 +ُ 3221 +ꯅ 3127 +ꯁ 2912 +ഔ 2763 +ଢ 2589 +ঢ 2569 +ಃ 2484 +ꯕ 2478 +ꯨ 2478 +ꯔ 2459 +ഢ 2452 +ఛ 2444 +ꯣ 2425 +ꯂ 2375 +ڊ 2363 +ꯡ 2303 +ഃ 2244 +අ 2236 +ୌ 2231 +ٲ 2156 +ꯗ 2118 +ః 2115 +ୈ 2105 +ꯟ 2039 +ණ 2024 +බ 1971 +ꯃ 1950 +ං 1935 +ꯄ 1853 +ො 1833 +ꯒ 1823 +ꯦ 1761 +ශ 1743 +ꯝ 1719 +ꯇ 1712 +ಔ 1695 +ꯛ 1671 +ෂ 1605 +ਢ 1588 +ઃ 1553 +ۍ 1539 +ڏ 1388 +ෝ 1376 +ජ 1351 +ژ 1277 +ධ 1275 +ꯀ 1259 +ٚ 1219 +ಋ 1218 +ڀ 1215 +ڌ 1207 +ٿ 1136 +ઊ 1136 +ڳ 1127 +ಝ 1106 +ঐ 1094 +භ 1072 +ꯈ 1070 +ච 1063 +ٔ 1060 +ٗ 1051 +ළ 1032 +ꯌ 1024 +ఔ 1023 +ꯊ 1022 +ଃ 1019 +ꯍ 1015 +ٮ 993 +ڇ 991 +ඩ 987 +۪ 950 +ٖ 945 +ූ 933 +ꯆ 932 +ٛ 916 +ഋ 913 +ঋ 890 +ఢ 878 +ꯩ 870 +ঈ 863 +ꯑ 839 +ۄ 810 +ꯐ 810 +ආ 804 +ؤ 778 +ઔ 761 +ٻ 759 +ٺ 721 +ꯠ 708 +ꯜ 703 +ꯢ 680 +උ 647 +ఋ 612 +ઋ 610 +ෘ 603 +ڦ 587 +ॄ 567 +ꯧ 530 +ꯏ 528 +ථ 524 +ꯖ 520 +ꯋ 484 +ঔ 479 +ඳ 478 +ਔ 457 +꯭ 443 +ැ 441 +ꯉ 422 +ඉ 420 +එ 419 +ఝ 405 +ꯎ 385 +ꯪ 374 +ڍ 370 +ۃ 360 +ঊ 353 +ڄ 332 +ଋ 325 +ّ 272 +ඟ 266 +ꯞ 242 +ڃ 222 +ઐ 204 +ॆ 196 +ඛ 185 +ඹ 172 +ඨ 163 +ଔ 162 +ඔ 151 +ඝ 147 +ඥ 145 +ଐ 140 +ෞ 137 +ꯚ 137 +ෛ 126 +ڱ 121 +ૅ 117 +ઑ 111 +ෆ 108 +ඡ 107 +ඵ 81 +ଈ 78 +ऍ 63 +ඇ 60 +ඊ 57 +ඒ 49 +॰ 47 +ഝ 46 +ඬ 38 +ෑ 38 +ඤ 35 +ඕ 32 +ꯓ 32 +ۭ 29 +ఱ 29 +ॊ 26 +، 25 +ઍ 24 +ఁ 24 +ꯙ 23 +ඍ 22 +ة 20 +ఙ 20 +ඖ 16 +ෲ 15 +ً 14 +ۓ 13 +૰ 13 +ꯘ 13 +઼ 12 +২ 11 +ઁ 10 +ඪ 10 +ඓ 9 +ਞ 8 +ඌ 8 +ඞ 8 +ॠ 7 +ؐ 6 +ඃ 6 +। 5 +ـ 4 +ਙ 4 +ඣ 4 +ك 3 +ऒ 3 +ٰ 2 +ॐ 2 +ଊ 2 +ෟ 2 +ؓ 1 +ٌ 1 +ٓ 1 +۶ 1 +۾ 1 +ऌ 1 +॑ 1 +॥ 1 +ੲ 1 +ૐ 1 +ୢ 1 +ஔ 1 +ౄ 1 +಼ 1 +ඈ 1 +madeupword0000 0 +madeupword0001 0 +madeupword0002 0 +madeupword0003 0 +madeupword0004 0 diff --git a/models/indic2en/model_checkpoint.pt b/models/indic2en/model_checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5ca51b2e167e9794a6831d29503df42504120da --- /dev/null +++ b/models/indic2en/model_checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ffecef88d990ae12f915939b91267a3fc8f69f26331baa59f7932005976f28 +size 135825281 diff --git a/models/indic2en/transformer/indicxlit.pt b/models/indic2en/transformer/indicxlit.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5ca51b2e167e9794a6831d29503df42504120da --- /dev/null +++ b/models/indic2en/transformer/indicxlit.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ffecef88d990ae12f915939b91267a3fc8f69f26331baa59f7932005976f28 +size 135825281 diff --git a/setup.py b/setup.py new file mode 100644 index 0000000000000000000000000000000000000000..fb7cdb82501947ce3f407638c646b102be2cbae3 --- /dev/null +++ b/setup.py @@ -0,0 +1,53 @@ +import pathlib +from setuptools import setup, find_packages +import pkg_resources + +# The directory containing this file +HERE = pathlib.Path(__file__).parent + +# The text of the README file +README = (HERE / "README.md").read_text(encoding='utf-8') + +with pathlib.Path('dependencies.txt').open() as requirements_txt: + install_requires = [ + str(requirement) + for requirement + in pkg_resources.parse_requirements(requirements_txt) + ] + +# Read meta-data +about = {} +exec(open('app/ai4bharat/transliteration/__metadata.py').read(), about) + +# This call to setup() does all the work +setup( + name="ai4bharat-transliteration", + version=about["__version__"], + description="Indic-Xlit: Transliteration library for Indic Languages. Conversion of text from English to 21 languages of South Asia.", + long_description=README, + long_description_content_type="text/markdown", + url="https://github.com/AI4Bharat/IndicXlit", + project_urls={ + # 'Say Thanks': 'mailto:opensource@ai4bharat.org', + 'Our Research': 'https://ai4bharat.org/transliteration', + 'Demo Website': 'https://xlit.ai4bharat.org', + 'Report Issues': 'https://github.com/AI4Bharat/IndicXlit/issues', + 'Source Code': 'https://github.com/AI4Bharat/IndicXlit/tree/master/app', + }, + author="AI4Bhārat", + author_email="opensource@ai4bharat.org", + # packages=["ai4bharat.transliteration"], + packages=find_packages(exclude=("tests",)), + # packages=find_packages(include=('ai4bharat.transliteration*')), + include_package_data=True, + install_requires=install_requires, + python_requires='>=3.6', + license='MIT', + classifiers=[ + "Programming Language :: Python :: 3", + "License :: OSI Approved :: MIT License", + "Operating System :: OS Independent", + "Topic :: Scientific/Engineering :: Artificial Intelligence", + "Topic :: Software Development :: Libraries" + ], +)