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