Hugging Face's logo

excalibur12
/
wav2vec2-large-lv60_phoneme-timit_english_timit-4k_simplified_001

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
excalibur12 commited on
Commit
52135b2
•
1 Parent(s): bb7b3c9

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +46 -40
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 49,
3
- "<s>": 48
4
  }
 
1
  {
2
+ "</s>": 55,
3
+ "<s>": 54
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "46": {
4
  "content": "[UNK]",
5
  "lstrip": false,
6
  "normalized": true,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "47": {
12
  "content": "[PAD]",
13
  "lstrip": false,
14
  "normalized": true,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "48": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "49": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "52": {
4
  "content": "[UNK]",
5
  "lstrip": false,
6
  "normalized": true,
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "53": {
12
  "content": "[PAD]",
13
  "lstrip": false,
14
  "normalized": true,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "54": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "55": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
vocab.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "[PAD]": 47,
3
- "[UNK]": 46,
4
  "aa": 0,
5
  "ae": 1,
6
  "ah": 2,
@@ -9,42 +9,48 @@
9
  "ax": 5,
10
  "ay": 6,
11
  "b": 7,
12
- "ch": 8,
13
- "d": 9,
14
- "dh": 10,
15
- "dx": 11,
16
- "eh": 12,
17
- "el": 13,
18
- "epi": 14,
19
- "er": 15,
20
- "ey": 16,
21
- "f": 17,
22
- "g": 18,
23
- "h#": 19,
24
- "hh": 20,
25
- "ih": 21,
26
- "iy": 22,
27
- "jh": 23,
28
- "k": 24,
29
- "l": 25,
30
- "m": 26,
31
- "n": 27,
32
- "ng": 28,
33
- "ow": 29,
34
- "oy": 30,
35
- "p": 31,
36
- "pau": 32,
37
- "q": 33,
38
- "r": 34,
39
- "s": 35,
40
- "sh": 36,
41
- "t": 37,
42
- "th": 38,
43
- "uh": 39,
44
- "uw": 40,
45
- "v": 41,
46
- "w": 42,
47
- "y": 43,
48
- "z": 44,
49
- "|": 45
 
 
 
 
 
 
50
  }
 
1
  {
2
+ "[PAD]": 53,
3
+ "[UNK]": 52,
4
  "aa": 0,
5
  "ae": 1,
6
  "ah": 2,
 
9
  "ax": 5,
10
  "ay": 6,
11
  "b": 7,
12
+ "bcl": 8,
13
+ "ch": 9,
14
+ "d": 10,
15
+ "dcl": 11,
16
+ "dh": 12,
17
+ "dx": 13,
18
+ "eh": 14,
19
+ "el": 15,
20
+ "epi": 16,
21
+ "er": 17,
22
+ "ey": 18,
23
+ "f": 19,
24
+ "g": 20,
25
+ "gcl": 21,
26
+ "h#": 22,
27
+ "hh": 23,
28
+ "ih": 24,
29
+ "iy": 25,
30
+ "jh": 26,
31
+ "k": 27,
32
+ "kcl": 28,
33
+ "l": 29,
34
+ "m": 30,
35
+ "n": 31,
36
+ "ng": 32,
37
+ "ow": 33,
38
+ "oy": 34,
39
+ "p": 35,
40
+ "pau": 36,
41
+ "pcl": 37,
42
+ "q": 38,
43
+ "r": 39,
44
+ "s": 40,
45
+ "sh": 41,
46
+ "t": 42,
47
+ "tcl": 43,
48
+ "th": 44,
49
+ "uh": 45,
50
+ "uw": 46,
51
+ "v": 47,
52
+ "w": 48,
53
+ "y": 49,
54
+ "z": 50,
55
+ "|": 51
56
  }