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