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
46069aa
•
1 Parent(s): 588c6b4

Upload tokenizer

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