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>": 45, "</s>": 46}
|
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 |
+
{"л": 0, "ӷ": 1, "а": 2, "ж": 3, "п": 4, "м": 5, "ф": 6, "ҟ": 7, "е": 8, "қ": 9, "и": 10, "с": 11, "н": 12, "ь": 13, "ҽ": 14, "ҳ": 15, "ҷ": 16, "–": 17, "в": 18, "р": 19, "c": 20, "џ": 21, "ш": 22, "г": 23, "д": 24, "ц": 25, "у": 26, "т": 27, "ԥ": 28, "ҵ": 29, "о": 30, "ы": 31, "ӡ": 32, "ҩ": 33, "ҭ": 34, "ч": 35, "з": 36, "б": 37, "ҿ": 39, "ә": 40, "к": 41, "х": 42, "|": 38, "[UNK]": 43, "[PAD]": 44}
|