Hugging Face's logo

Roxysun
/
cs2no_wav2vec2-large-xls-r-300m-czech-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Roxysun commited on
Commit
18efa11
•
1 Parent(s): 4bc5e0d

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +41 -68
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 71,
3
- "<s>": 70
4
  }
 
1
  {
2
+ "</s>": 44,
3
+ "<s>": 43
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "68": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "69": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "70": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "71": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "41": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "42": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "43": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "44": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
vocab.json CHANGED
@@ -1,72 +1,45 @@
1
  {
2
  "!": 1,
3
- "%": 2,
4
- "'": 3,
5
- ",": 4,
6
- "-": 5,
7
- ".": 6,
8
- "?": 7,
9
- "A": 8,
10
- "B": 9,
11
- "C": 10,
12
- "D": 11,
13
- "E": 12,
14
- "F": 13,
15
- "G": 14,
16
- "H": 15,
17
- "I": 16,
18
- "J": 17,
19
- "K": 18,
20
- "L": 19,
21
- "M": 20,
22
- "N": 21,
23
- "O": 22,
24
- "P": 23,
25
- "R": 24,
26
- "S": 25,
27
- "T": 26,
28
- "U": 27,
29
- "V": 28,
30
- "W": 29,
31
- "[PAD]": 69,
32
- "[UNK]": 68,
33
- "\\": 30,
34
- "_": 31,
35
- "a": 32,
36
- "b": 33,
37
- "c": 34,
38
- "d": 35,
39
- "e": 36,
40
- "f": 37,
41
- "g": 38,
42
- "h": 39,
43
- "i": 40,
44
- "j": 41,
45
- "k": 42,
46
- "l": 43,
47
- "m": 44,
48
- "n": 45,
49
- "o": 46,
50
- "p": 47,
51
- "q": 48,
52
- "r": 49,
53
- "s": 50,
54
- "t": 51,
55
- "u": 52,
56
- "v": 53,
57
- "w": 54,
58
- "x": 55,
59
- "y": 56,
60
- "z": 57,
61
  "|": 0,
62
- "£": 58,
63
- "Å": 59,
64
- "Ø": 60,
65
- "å": 61,
66
- "æ": 62,
67
- "è": 63,
68
- "é": 64,
69
- "ò": 65,
70
- "ø": 66,
71
- "ü": 67
72
  }
 
1
  {
2
  "!": 1,
3
+ "'": 2,
4
+ ".": 3,
5
+ "?": 4,
6
+ "[PAD]": 42,
7
+ "[UNK]": 41,
8
+ "\\": 5,
9
+ "_": 6,
10
+ "a": 7,
11
+ "b": 8,
12
+ "c": 9,
13
+ "d": 10,
14
+ "e": 11,
15
+ "f": 12,
16
+ "g": 13,
17
+ "h": 14,
18
+ "i": 15,
19
+ "j": 16,
20
+ "k": 17,
21
+ "l": 18,
22
+ "m": 19,
23
+ "n": 20,
24
+ "o": 21,
25
+ "p": 22,
26
+ "q": 23,
27
+ "r": 24,
28
+ "s": 25,
29
+ "t": 26,
30
+ "u": 27,
31
+ "v": 28,
32
+ "w": 29,
33
+ "x": 30,
34
+ "y": 31,
35
+ "z": 32,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  "|": 0,
37
+ "£": 33,
38
+ "å": 34,
39
+ "æ": 35,
40
+ "è": 36,
41
+ "é": 37,
42
+ "ò": 38,
43
+ "ø": 39,
44
+ "ü": 40
 
 
45
  }