AigizK commited on
Commit
e0ec8c9
1 Parent(s): 52c38a4

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 39, "</s>": 40}
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
+ {"а": 1, "б": 2, "в": 3, "г": 4, "д": 5, "ж": 6, "з": 7, "и": 8, "й": 9, "к": 10, "л": 11, "м": 12, "н": 13, "о": 14, "п": 15, "р": 16, "с": 17, "т": 18, "у": 19, "ф": 20, "х": 21, "ц": 22, "ч": 23, "ш": 24, "щ": 25, "ы": 26, "э": 27, "ғ": 28, "ҙ": 29, "ҡ": 30, "ң": 31, "ҫ": 32, "ү": 33, "һ": 34, "ә": 35, "ө": 36, "|": 0, "[UNK]": 37, "[PAD]": 38}