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 @@
+{"श": 0, "उ": 1, "ः": 2, "ृ": 3, "भ": 4, "य": 5, "त": 6, "द": 7, "न": 9, "र": 10, "्": 11, "स": 12, "प": 13, "ह": 14, "म": 15, "ा": 16, "ण": 17, "व": 18, "ु": 19, "अ": 20, "क": 21, "च": 22, "े": 23, "ज": 24, "ख": 25, "ी": 26, "ि": 27, "इ": 28, "आ": 29, "ष": 30, "ड": 31, "ै": 32, "ङ": 33, "ू": 34, "ग": 35, "ं": 36, "ो": 37, "ध": 38, "थ": 39, "ट": 40, "ल": 41, "फ": 42, "ञ": 43, "घ": 44, "ब": 45, "ठ": 46, "ए": 47, "ौ": 48, "ऐ": 49, "ढ": 50, "ऽ": 51, "छ": 52, "ऊ": 53, "ई": 54, "औ": 55, "ओ": 56, "झ": 57, "ळ": 58, "ऋ": 59, "ॄ": 60, "|": 8, "[UNK]": 61, "[PAD]": 62}