add tokenizer
Browse files- added_tokens.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>": 73, "</s>": 74}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"F": 1, "M": 2, "W": 3, "a": 4, "e": 5, "i": 6, "l": 7, "m": 8, "p": 9, "r": 10, "u": 11, "ँ": 12, "ं": 13, "ः": 14, "अ": 15, "आ": 16, "इ": 17, "ई": 18, "उ": 19, "ऊ": 20, "ए": 21, "ऐ": 22, "ऑ": 23, "ओ": 24, "औ": 25, "क": 26, "ख": 27, "ग": 28, "घ": 29, "च": 30, "छ": 31, "ज": 32, "झ": 33, "ट": 34, "ठ": 35, "ड": 36, "ढ": 37, "ण": 38, "त": 39, "थ": 40, "द": 41, "ध": 42, "न": 43, "प": 44, "फ": 45, "ब": 46, "भ": 47, "म": 48, "य": 49, "र": 50, "ल": 51, "व": 52, "श": 53, "ष": 54, "स": 55, "ह": 56, "़": 57, "ा": 58, "ि": 59, "ी": 60, "ु": 61, "ू": 62, "ृ": 63, "े": 64, "ै": 65, "ॉ": 66, "ो": 67, "ौ": 68, "्": 69, "ड़": 70, "|": 0, "[UNK]": 71, "[PAD]": 72}
|