kika2000 commited on
Commit
91bda72
1 Parent(s): 42e6a67

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 36, "</s>": 37}
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
+ {"ა": 1, "ბ": 2, "გ": 3, "დ": 4, "ე": 5, "ვ": 6, "ზ": 7, "თ": 8, "ი": 9, "კ": 10, "ლ": 11, "მ": 12, "ნ": 13, "ო": 14, "პ": 15, "ჟ": 16, "რ": 17, "ს": 18, "ტ": 19, "უ": 20, "ფ": 21, "ქ": 22, "ღ": 23, "ყ": 24, "შ": 25, "ჩ": 26, "ც": 27, "ძ": 28, "წ": 29, "ჭ": 30, "ხ": 31, "ჯ": 32, "ჰ": 33, "|": 0, "[UNK]": 34, "[PAD]": 35}