Hugging Face's logo

TheRamsay
/
wav2vec2-large-cs-colab

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Model card Files
xet
 Community
TheRamsay commited on
Commit
5244f76
·
verified ·
1 Parent(s): 35d5abf

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +18 -21
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 50,
3
- "<s>": 49
4
  }
 
1
  {
2
+ "</s>": 47,
3
+ "<s>": 46
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "47": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "48": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "49": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "50": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "44": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "45": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "46": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "47": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "[PAD]": 48,
3
- "[UNK]": 47,
4
  "a": 1,
5
  "b": 2,
6
  "c": 3,
@@ -29,23 +29,20 @@
29
  "z": 26,
30
  "|": 0,
31
  "á": 27,
32
- "ä": 28,
33
- "è": 29,
34
- "é": 30,
35
- "í": 31,
36
- "ï": 32,
37
- "ó": 33,
38
- "ö": 34,
39
- "ú": 35,
40
- "ü": 36,
41
- "ý": 37,
42
- "č": 38,
43
- "ď": 39,
44
- "ě": 40,
45
- "ň": 41,
46
- "ř": 42,
47
- "š": 43,
48
- "ť": 44,
49
- "ů": 45,
50
- "ž": 46
51
  }
 
1
  {
2
+ "[PAD]": 45,
3
+ "[UNK]": 44,
4
  "a": 1,
5
  "b": 2,
6
  "c": 3,
 
29
  "z": 26,
30
  "|": 0,
31
  "á": 27,
32
+ "é": 28,
33
+ "í": 29,
34
+ "ó": 30,
35
+ "ö": 31,
36
+ "ú": 32,
37
+ "ü": 33,
38
+ "ý": 34,
39
+ "č": 35,
40
+ "ď": 36,
41
+ "ě": 37,
42
+ "ň": 38,
43
+ "ř": 39,
44
+ "š": 40,
45
+ "ť": 41,
46
+ "ů": 42,
47
+ "ž": 43
 
 
 
48
  }