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>": 47, "</s>": 48}
|
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 |
+
{"й": 0, "о": 1, "э": 2, "i": 3, "ҕ": 4, "л": 5, "ө": 6, "м": 7, "ф": 8, "б": 9, "ч": 10, "ҥ": 11, "c": 12, "в": 13, "»": 14, "ж": 15, "ь": 16, "һ": 17, "н": 18, "ю": 20, "з": 21, "и": 22, "д": 23, "р": 24, "і": 25, "т": 26, "ц": 27, "ш": 28, "п": 29, "«": 30, "щ": 31, "o": 32, "г": 33, "ы": 34, "у": 35, "а": 36, "к": 37, "ј": 38, "х": 39, "с": 40, "е": 41, "я": 42, "ү": 43, "y": 44, "|": 19, "[UNK]": 45, "[PAD]": 46}
|