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