Hugging Face's logo

paruwka
/
wav2vec2-base-timit-demo-google-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
paruwka commited on
Commit
b87d5ff
•
1 Parent(s): a56af9c

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +4 -2
  2. tokenizer_config.json +10 -10
  3. vocab.json +64 -66
added_tokens.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
- "</s>": 69,
3
- "<s>": 68
 
 
4
  }
 
1
  {
2
+ "</s>": 67,
3
+ "<s>": 66,
4
+ "[PAD]": 69,
5
+ "[UNK]": 68
6
  }
tokenizer_config.json CHANGED
@@ -1,23 +1,23 @@
1
  {
2
  "added_tokens_decoder": {
3
  "66": {
4
- "content": "[UNK]",
5
- "lstrip": true,
6
  "normalized": false,
7
- "rstrip": true,
8
  "single_word": false,
9
- "special": false
10
  },
11
  "67": {
12
- "content": "[PAD]",
13
- "lstrip": true,
14
  "normalized": false,
15
- "rstrip": true,
16
  "single_word": false,
17
- "special": false
18
  },
19
  "68": {
20
- "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,7 +25,7 @@
25
  "special": true
26
  },
27
  "69": {
28
- "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
1
  {
2
  "added_tokens_decoder": {
3
  "66": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
  "normalized": false,
7
+ "rstrip": false,
8
  "single_word": false,
9
+ "special": true
10
  },
11
  "67": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
  "normalized": false,
15
+ "rstrip": false,
16
  "single_word": false,
17
+ "special": true
18
  },
19
  "68": {
20
+ "content": "[UNK]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "69": {
28
+ "content": "[PAD]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
vocab.json CHANGED
@@ -1,70 +1,68 @@
1
  {
2
- "&": 16,
3
- "'": 51,
4
- "(": 37,
5
- ")": 48,
6
- "=": 36,
7
- "[PAD]": 67,
8
- "[UNK]": 66,
9
- "a": 46,
10
  "b": 6,
11
- "c": 57,
12
- "d": 1,
13
- "e": 27,
14
- "f": 47,
15
- "g": 5,
16
- "h": 2,
17
- "i": 52,
18
- "j": 61,
19
- "k": 13,
20
- "l": 31,
21
- "m": 7,
22
- "n": 50,
23
- "o": 45,
24
- "p": 32,
25
- "q": 12,
26
- "r": 53,
27
- "s": 19,
28
  "t": 22,
29
- "u": 20,
30
- "v": 41,
31
- "w": 21,
32
- "x": 40,
33
- "y": 29,
34
- "z": 25,
35
- "|": 59,
36
- "«": 30,
37
- "»": 10,
38
- "ß": 55,
39
- "à": 15,
40
- "á": 49,
41
- "â": 54,
42
- "ç": 24,
43
- "è": 33,
44
- "é": 11,
45
- "ê": 14,
46
- "ë": 65,
47
- "î": 39,
48
- "ï": 62,
49
- "ó": 3,
50
- "ô": 58,
51
- "ö": 28,
52
- "ø": 64,
53
- "ù": 0,
54
- "ú": 44,
55
- "û": 23,
56
- "ü": 9,
57
- "ć": 60,
58
- "ē": 35,
59
- "ō": 42,
60
- "œ": 56,
61
- "š": 26,
62
- "ū": 18,
63
- "̀": 8,
64
- "́": 38,
65
- "̂": 43,
66
- "̧": 4,
67
- "—": 63,
68
- "’": 34,
69
- "…": 17
70
  }
 
1
  {
2
+ " ": 17,
3
+ "&": 12,
4
+ "'": 39,
5
+ "(": 19,
6
+ ")": 8,
7
+ "=": 46,
8
+ "a": 36,
 
9
  "b": 6,
10
+ "c": 16,
11
+ "d": 50,
12
+ "e": 41,
13
+ "f": 44,
14
+ "g": 10,
15
+ "h": 4,
16
+ "i": 15,
17
+ "j": 2,
18
+ "k": 11,
19
+ "l": 28,
20
+ "m": 25,
21
+ "n": 55,
22
+ "o": 48,
23
+ "p": 21,
24
+ "q": 5,
25
+ "r": 49,
26
+ "s": 29,
27
  "t": 22,
28
+ "u": 52,
29
+ "v": 57,
30
+ "w": 32,
31
+ "x": 31,
32
+ "y": 37,
33
+ "z": 33,
34
+ "«": 20,
35
+ "»": 56,
36
+ "ß": 42,
37
+ "à": 26,
38
+ "á": 40,
39
+ "â": 47,
40
+ "ç": 27,
41
+ "è": 3,
42
+ "é": 23,
43
+ "ê": 34,
44
+ "ë": 64,
45
+ "î": 30,
46
+ "ï": 60,
47
+ "ó": 51,
48
+ "ô": 7,
49
+ "ö": 54,
50
+ "ø": 14,
51
+ "ù": 65,
52
+ "ú": 62,
53
+ "û": 61,
54
+ "ü": 53,
55
+ "ć": 43,
56
+ "ē": 63,
57
+ "ō": 38,
58
+ "œ": 18,
59
+ "š": 59,
60
+ "ū": 13,
61
+ "̀": 1,
62
+ "́": 45,
63
+ "̂": 9,
64
+ "̧": 58,
65
+ "—": 24,
66
+ "’": 35,
67
+ "…": 0
 
68
  }