add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"प": 0, "न": 2, "ी": 3, "ह": 4, "ख": 5, "य": 6, "ड़": 7, "च": 8, "l": 9, "घ": 10, "़": 11, "स": 12, "e": 13, "म": 14, "ध": 15, "ज": 16, "ओ": 17, "ा": 18, "झ": 19, "w": 20, "्": 21, "m": 22, "'": 23, "f": 24, "ऑ": 25, "थ": 26, "उ": 27, "ऊ": 28, "ौ": 29, "ृ": 30, "इ": 31, "p": 32, "ँ": 33, "श": 34, "ढ": 35, "ऐ": 36, "ई": 37, "ि": 38, "त": 39, "ष": 40, "छ": 41, "द": 42, "ू": 43, "।": 44, "क": 45, "ड": 46, "ल": 47, "आ": 48, "ण": 49, "औ": 50, "ु": 51, "अ": 52, "व": 53, "ः": 54, "र": 55, "फ": 56, "ै": 57, "r": 58, "ॉ": 59, "ब": 60, "ो": 61, "i": 62, "ट": 63, "ठ": 64, "ग": 65, "े": 66, "भ": 67, "ं": 68, "ए": 69, "a": 70, "u": 71, "|": 1, "[UNK]": 72, "[PAD]": 73}