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
d519b28
•
1 Parent(s): 5ef032c

Upload tokenizer

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