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>": 54, "</s>": 55}
|
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 |
+
{"г": 0, "r": 1, "«": 2, "е": 3, "п": 4, "ё": 5, "ч": 6, "ә": 7, "э": 8, "щ": 9, "a": 10, "»": 11, "и": 12, "р": 13, "в": 14, "ц": 15, "x": 16, "с": 17, "к": 18, "у": 19, "з": 20, "я": 21, "ү": 22, "л": 23, "t": 24, "х": 25, "җ": 26, "б": 27, "й": 28, "м": 29, "o": 30, "а": 31, "ө": 32, "н": 33, "ж": 34, "һ": 35, "ң": 36, "e": 37, "i": 38, "ф": 39, "f": 40, "о": 41, "ш": 42, "–": 43, "ъ": 44, "—": 45, "ю": 46, "д": 48, "ь": 49, "т": 50, "ы": 51, "|": 47, "[UNK]": 52, "[PAD]": 53}
|