add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 38, "</s>": 39}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"ء": 1, "ا": 2, "ب": 3, "ة": 4, "ت": 5, "ث": 6, "ج": 7, "ح": 8, "خ": 9, "د": 10, "ذ": 11, "ر": 12, "ز": 13, "س": 14, "ش": 15, "ص": 16, "ض": 17, "ط": 18, "ظ": 19, "ع": 20, "غ": 21, "ف": 22, "ق": 23, "ك": 24, "ل": 25, "م": 26, "ن": 27, "ه": 28, "و": 29, "ى": 30, "ي": 31, "ک": 32, "ھ": 33, "ی": 34, "ﻻ": 35, "|": 0, "[UNK]": 36, "[PAD]": 37}