Commit
•
b0b365b
1
Parent(s):
ff3b934
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 |
+
{"e": 1, "m": 2, "p": 3, "r": 4, "u": 5, "w": 6, "ँ": 7, "ं": 8, "ः": 9, "अ": 10, "आ": 11, "इ": 12, "ई": 13, "उ": 14, "ऊ": 15, "ए": 16, "ऐ": 17, "ऑ": 18, "ओ": 19, "औ": 20, "क": 21, "ख": 22, "ग": 23, "घ": 24, "च": 25, "छ": 26, "ज": 27, "झ": 28, "ट": 29, "ठ": 30, "ड": 31, "ढ": 32, "ण": 33, "त": 34, "थ": 35, "द": 36, "ध": 37, "न": 38, "प": 39, "फ": 40, "ब": 41, "भ": 42, "म": 43, "य": 44, "र": 45, "ल": 46, "व": 47, "श": 48, "ष": 49, "स": 50, "ह": 51, "़": 52, "ा": 53, "ि": 54, "ी": 55, "ु": 56, "ू": 57, "ृ": 58, "े": 59, "ै": 60, "ॉ": 61, "ो": 62, "ौ": 63, "्": 64, "ड़": 65, "|": 0, "[UNK]": 66, "[PAD]": 67}
|