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
ccecdba
·
verified ·
1 Parent(s): 0bb1c14

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +3 -3
  2. added_tokens.json +2 -2
  3. tokenizer_config.json +4 -4
  4. vocab.json +47 -44
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
- license: apache-2.0
3
  base_model: facebook/wav2vec2-base
4
- tags:
5
- - generated_from_trainer
6
  datasets:
7
  - transcribed_calls
 
 
 
8
  model-index:
9
  - name: wav2vec2-base-wonders-phonemes
10
  results: []
 
1
  ---
 
2
  base_model: facebook/wav2vec2-base
 
 
3
  datasets:
4
  - transcribed_calls
5
+ license: apache-2.0
6
+ tags:
7
+ - generated_from_trainer
8
  model-index:
9
  - name: wav2vec2-base-wonders-phonemes
10
  results: []
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 45,
3
- "<s>": 44
4
  }
 
1
  {
2
+ "</s>": 48,
3
+ "<s>": 47
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "42": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "43": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "44": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "45": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "45": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "46": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "47": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "48": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,46 +1,49 @@
1
  {
2
- "[PAD]": 43,
3
- "[UNK]": 42,
4
- "a": 29,
5
- "b": 19,
6
- "d": 33,
7
- "e": 35,
8
- "f": 39,
9
- "h": 14,
10
- "i": 15,
11
- "j": 1,
12
- "k": 34,
13
- "l": 9,
14
- "m": 13,
15
- "n": 21,
16
- "o": 40,
17
- "p": 24,
18
- "s": 0,
19
- "t": 26,
20
- "u": 36,
21
- "v": 12,
22
- "w": 41,
23
- "z": 5,
24
- "|": 23,
25
- "æ": 6,
26
- "ð": 32,
27
- "ŋ": 17,
28
- "ɐ": 4,
29
- "ɑ": 30,
30
- "ɔ": 22,
31
- "ə": 18,
32
- "ɚ": 7,
33
- "ɛ": 2,
34
- "ɜ": 31,
35
- "ɡ": 38,
36
- "ɪ": 11,
37
- "ɹ": 10,
38
- "ɾ": 37,
39
- "ʃ": 28,
40
- "ʊ": 8,
41
- "ʌ": 3,
42
- "ʒ": 20,
43
- "ː": 25,
44
- "θ": 16,
45
- "ᵻ": 27
 
 
 
46
  }
 
1
  {
2
+ "[PAD]": 46,
3
+ "[UNK]": 45,
4
+ "a": 2,
5
+ "b": 31,
6
+ "d": 13,
7
+ "e": 8,
8
+ "f": 1,
9
+ "h": 0,
10
+ "i": 38,
11
+ "j": 41,
12
+ "k": 33,
13
+ "l": 39,
14
+ "m": 17,
15
+ "n": 29,
16
+ "o": 7,
17
+ "p": 10,
18
+ "s": 16,
19
+ "t": 20,
20
+ "u": 9,
21
+ "v": 28,
22
+ "w": 15,
23
+ "z": 27,
24
+ "|": 14,
25
+ "æ": 22,
26
+ "ð": 11,
27
+ "ŋ": 12,
28
+ "ɐ": 18,
29
+ "ɑ": 3,
30
+ "ɔ": 4,
31
+ "ə": 26,
32
+ "ɚ": 42,
33
+ "ɛ": 34,
34
+ "ɜ": 19,
35
+ "ɡ": 32,
36
+ "ɣ": 21,
37
+ "ɪ": 6,
38
+ "ɹ": 43,
39
+ "ɾ": 5,
40
+ "ʃ": 30,
41
+ "ʊ": 36,
42
+ "ʌ": 44,
43
+ "ʒ": 35,
44
+ "ʔ": 37,
45
+ "ː": 40,
46
+ "̩": 24,
47
+ "θ": 23,
48
+ "ᵻ": 25
49
  }