Hugging Face's logo

mattbonnell
/
wav2vec2-base-wonders-phonemes

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
mattbonnell commited on
Commit
5dd74f5
·
verified ·
1 Parent(s): ca958dd

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +45 -47
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 48,
3
- "<s>": 47
4
  }
 
1
  {
2
+ "</s>": 46,
3
+ "<s>": 45
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "45": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "46": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "47": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "48": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "43": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "44": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "45": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "46": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,49 +1,47 @@
1
  {
2
- "[PAD]": 46,
3
- "[UNK]": 45,
4
- "a": 27,
5
- "b": 0,
6
- "d": 5,
7
- "e": 6,
8
- "f": 31,
9
- "h": 16,
10
- "i": 24,
11
- "j": 21,
12
- "k": 25,
13
- "l": 42,
14
- "m": 38,
15
- "n": 15,
16
- "o": 35,
17
- "p": 32,
18
- "s": 3,
19
- "t": 18,
20
- "u": 14,
21
- "v": 12,
22
- "w": 37,
23
- "z": 40,
24
- "|": 1,
25
- "æ": 22,
26
- "ð": 11,
27
- "ŋ": 43,
28
- "ɐ": 26,
29
- "ɑ": 4,
30
- "ɔ": 33,
31
- "ə": 39,
32
- "ɚ": 8,
33
- "ɛ": 2,
34
- "ɜ": 23,
35
- "ɡ": 30,
36
- "ɣ": 9,
37
- "ɪ": 28,
38
- "ɹ": 10,
39
- "ɾ": 17,
40
- "ʃ": 36,
41
- "ʊ": 34,
42
- "ʌ": 20,
43
- "ʒ": 44,
44
- "ʔ": 7,
45
- "ː": 29,
46
- "̩": 41,
47
- "θ": 13,
48
- "ᵻ": 19
49
  }
 
1
  {
2
+ "[PAD]": 44,
3
+ "[UNK]": 43,
4
+ "a": 25,
5
+ "b": 13,
6
+ "d": 26,
7
+ "e": 40,
8
+ "f": 15,
9
+ "h": 5,
10
+ "i": 31,
11
+ "j": 23,
12
+ "k": 27,
13
+ "l": 38,
14
+ "m": 16,
15
+ "n": 33,
16
+ "o": 9,
17
+ "p": 2,
18
+ "s": 17,
19
+ "t": 10,
20
+ "u": 6,
21
+ "v": 7,
22
+ "w": 14,
23
+ "z": 35,
24
+ "|": 21,
25
+ "æ": 30,
26
+ "ð": 32,
27
+ "ŋ": 0,
28
+ "ɐ": 12,
29
+ "ɑ": 22,
30
+ "ɔ": 3,
31
+ "ə": 41,
32
+ "ɚ": 18,
33
+ "ɛ": 39,
34
+ "ɜ": 42,
35
+ "ɡ": 11,
36
+ "ɣ": 1,
37
+ "ɪ": 8,
38
+ "ɹ": 29,
39
+ "ɾ": 24,
40
+ "ʃ": 4,
41
+ "ʊ": 20,
42
+ "ʌ": 36,
43
+ "ʒ": 19,
44
+ "ː": 34,
45
+ "θ": 28,
46
+ "ᵻ": 37
 
 
47
  }