Commit
•
59da447
1
Parent(s):
0fea3b4
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>": 68, "</s>": 69}
|
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 |
+
{"a": 1, "f": 2, "i": 3, "l": 4, "m": 5, "p": 6, "r": 7, "w": 8, "ँ": 9, "ं": 10, "अ": 11, "आ": 12, "इ": 13, "ई": 14, "उ": 15, "ऊ": 16, "ए": 17, "ऐ": 18, "ऑ": 19, "ओ": 20, "औ": 21, "क": 22, "ख": 23, "ग": 24, "घ": 25, "च": 26, "छ": 27, "ज": 28, "झ": 29, "ट": 30, "ठ": 31, "ड": 32, "ढ": 33, "ण": 34, "त": 35, "थ": 36, "द": 37, "ध": 38, "न": 39, "प": 40, "फ": 41, "ब": 42, "भ": 43, "म": 44, "य": 45, "र": 46, "ल": 47, "व": 48, "श": 49, "ष": 50, "स": 51, "ह": 52, "़": 53, "ा": 54, "ि": 55, "ी": 56, "ु": 57, "ू": 58, "े": 59, "ै": 60, "ॉ": 61, "ो": 62, "ौ": 63, "्": 64, "।": 65, "|": 0, "[UNK]": 66, "[PAD]": 67}
|