Commit
•
b1409c4
1
Parent(s):
60067dd
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>": 70, "</s>": 71}
|
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 |
+
{"ँ": 1, "ं": 2, "ः": 3, "अ": 4, "आ": 5, "इ": 6, "ई": 7, "उ": 8, "ऊ": 9, "ऋ": 10, "ए": 11, "ऐ": 12, "ऑ": 13, "ओ": 14, "औ": 15, "क": 16, "ख": 17, "ग": 18, "घ": 19, "च": 20, "छ": 21, "ज": 22, "झ": 23, "ञ": 24, "ट": 25, "ठ": 26, "ड": 27, "ढ": 28, "ण": 29, "त": 30, "थ": 31, "द": 32, "ध": 33, "न": 34, "प": 35, "फ": 36, "ब": 37, "भ": 38, "म": 39, "य": 40, "र": 41, "ऱ": 42, "ल": 43, "ळ": 44, "व": 45, "श": 46, "ष": 47, "स": 48, "ह": 49, "़": 50, "ा": 51, "ि": 52, "ी": 53, "ु": 54, "ू": 55, "ृ": 56, "ॄ": 57, "ॅ": 58, "े": 59, "ै": 60, "ॉ": 61, "ॊ": 62, "ो": 63, "ौ": 64, "्": 65, "॔": 66, "।": 67, "|": 0, "[UNK]": 68, "[PAD]": 69}
|