Hugging Face's logo

NX2411
/
wav2vec2-large-xlsr-korean-demo3

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
NX2411 commited on
Commit
0fe3920
β€’
1 Parent(s): 43fb1b4

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +10 -0
  3. vocab.json +53 -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 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "pad_token": "[PAD]",
6
+ "replace_word_delimiter_char": " ",
7
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
8
+ "unk_token": "[UNK]",
9
+ "word_delimiter_token": "|"
10
+ }
vocab.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 50,
3
+ "[UNK]": 49,
4
+ "|": 38,
5
+ "γ„±": 35,
6
+ "γ„²": 26,
7
+ "γ„³": 27,
8
+ "γ„΄": 12,
9
+ "γ„΅": 31,
10
+ "γ„Ά": 6,
11
+ "γ„·": 14,
12
+ "γ„Έ": 45,
13
+ "γ„Ή": 23,
14
+ "γ„Ί": 28,
15
+ "γ„»": 41,
16
+ "γ„Ό": 43,
17
+ "γ…€": 9,
18
+ "ㅁ": 29,
19
+ "γ…‚": 3,
20
+ "γ…ƒ": 17,
21
+ "γ…„": 2,
22
+ "γ……": 11,
23
+ "γ…†": 36,
24
+ "γ…‡": 19,
25
+ "γ…ˆ": 16,
26
+ "γ…‰": 7,
27
+ "γ…Š": 8,
28
+ "γ…‹": 25,
29
+ "γ…Œ": 42,
30
+ "ㅍ": 46,
31
+ "γ…Ž": 24,
32
+ "ㅏ": 10,
33
+ "ㅐ": 32,
34
+ "γ…‘": 39,
35
+ "γ…’": 5,
36
+ "γ…“": 22,
37
+ "γ…”": 20,
38
+ "γ…•": 40,
39
+ "γ…–": 44,
40
+ "γ…—": 47,
41
+ "γ…˜": 15,
42
+ "γ…™": 0,
43
+ "γ…š": 48,
44
+ "γ…›": 13,
45
+ "γ…œ": 34,
46
+ "ㅝ": 1,
47
+ "γ…ž": 33,
48
+ "γ…Ÿ": 4,
49
+ "γ… ": 30,
50
+ "γ…‘": 18,
51
+ "γ…’": 37,
52
+ "γ…£": 21
53
+ }