Hugging Face's logo

molto
/
ft_1

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
molto commited on
Commit
0d35ea9
Β·
1 Parent(s): 2b06a26

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +12 -0
  3. vocab.json +52 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 49,
3
+ "[UNK]": 48,
4
+ "|": 0,
5
+ "γ„±": 1,
6
+ "γ„²": 2,
7
+ "γ„΄": 3,
8
+ "γ„΅": 4,
9
+ "γ„Ά": 5,
10
+ "γ„·": 6,
11
+ "γ„Έ": 7,
12
+ "γ„Ή": 8,
13
+ "γ„Ί": 9,
14
+ "γ„»": 10,
15
+ "γ„Ό": 11,
16
+ "γ…€": 12,
17
+ "ㅁ": 13,
18
+ "γ…‚": 14,
19
+ "γ…ƒ": 15,
20
+ "γ…„": 16,
21
+ "γ……": 17,
22
+ "γ…†": 18,
23
+ "γ…‡": 19,
24
+ "γ…ˆ": 20,
25
+ "γ…‰": 21,
26
+ "γ…Š": 22,
27
+ "γ…‹": 23,
28
+ "γ…Œ": 24,
29
+ "ㅍ": 25,
30
+ "γ…Ž": 26,
31
+ "ㅏ": 27,
32
+ "ㅐ": 28,
33
+ "γ…‘": 29,
34
+ "γ…’": 30,
35
+ "γ…“": 31,
36
+ "γ…”": 32,
37
+ "γ…•": 33,
38
+ "γ…–": 34,
39
+ "γ…—": 35,
40
+ "γ…˜": 36,
41
+ "γ…™": 37,
42
+ "γ…š": 38,
43
+ "γ…›": 39,
44
+ "γ…œ": 40,
45
+ "ㅝ": 41,
46
+ "γ…ž": 42,
47
+ "γ…Ÿ": 43,
48
+ "γ… ": 44,
49
+ "γ…‘": 45,
50
+ "γ…’": 46,
51
+ "γ…£": 47
52
+ }