add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"स": 0, "झ": 1, "ष": 2, "न": 3, "ं": 4, "त": 5, "उ": 6, "ठ": 7, "ौ": 8, "ड": 9, "ृ": 10, "ँ": 11, "र": 12, "ू": 13, "ः": 14, "ह": 15, "ज": 16, "ा": 17, "ई": 18, "ध": 19, "ण": 20, "ओ": 21, "भ": 22, "ल": 23, "ि": 24, "ै": 25, "क": 26, "अ": 27, "": 28, "औ": 29, "थ": 30, "श": 31, "च": 32, "": 33, "ग": 34, "ु": 35, "प": 36, "ो": 37, "छ": 38, "ङ": 39, "आ": 40, "ब": 41, "ढ": 42, "म": 43, "ी": 44, "े": 45, "द": 46, "्": 47, "फ": 48, "य": 49, "ट": 50, "ख": 51, "ए": 52, "व": 54, "घ": 55, "ञ": 56, "इ": 57, "|": 53, "[UNK]": 58, "[PAD]": 59}
|