Commit
•
1c59cfa
1
Parent(s):
b5f394b
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 |
+
{"a": 1, "e": 2, "f": 3, "i": 4, "l": 5, "m": 6, "p": 7, "r": 8, "u": 9, "w": 10, "ँ": 11, "ं": 12, "ः": 13, "अ": 14, "आ": 15, "इ": 16, "ई": 17, "उ": 18, "ऊ": 19, "ए": 20, "ऐ": 21, "ऑ": 22, "ओ": 23, "औ": 24, "क": 25, "ख": 26, "ग": 27, "घ": 28, "च": 29, "छ": 30, "ज": 31, "झ": 32, "ट": 33, "ठ": 34, "ड": 35, "ढ": 36, "ण": 37, "त": 38, "थ": 39, "द": 40, "ध": 41, "न": 42, "प": 43, "फ": 44, "ब": 45, "भ": 46, "म": 47, "य": 48, "र": 49, "ल": 50, "व": 51, "श": 52, "ष": 53, "स": 54, "ह": 55, "़": 56, "ा": 57, "ि": 58, "ी": 59, "ु": 60, "ू": 61, "ृ": 62, "े": 63, "ै": 64, "ॉ": 65, "ो": 66, "ौ": 67, "्": 68, "ड़": 69, "।": 70, "|": 0, "[UNK]": 71, "[PAD]": 72}
|