mattbonnell commited on
Commit
6bfa643
·
verified ·
1 Parent(s): 3e37dee

Upload tokenizer

Browse files
Files changed (2) hide show
  1. README.md +4 -4
  2. vocab.json +42 -42
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
3
- base_model: facebook/wav2vec2-base
4
  tags:
5
  - generated_from_trainer
 
6
  datasets:
7
  - transcribed_calls
8
  metrics:
@@ -11,8 +11,8 @@ model-index:
11
  - name: wav2vec2-base-wonders-phonemes
12
  results:
13
  - task:
14
- name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
 
16
  dataset:
17
  name: transcribed_calls
18
  type: transcribed_calls
@@ -20,9 +20,9 @@ model-index:
20
  split: None
21
  args: default
22
  metrics:
23
- - name: Wer
24
- type: wer
25
  value: 1.0
 
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
+ base_model: facebook/wav2vec2-base
6
  datasets:
7
  - transcribed_calls
8
  metrics:
 
11
  - name: wav2vec2-base-wonders-phonemes
12
  results:
13
  - task:
 
14
  type: automatic-speech-recognition
15
+ name: Automatic Speech Recognition
16
  dataset:
17
  name: transcribed_calls
18
  type: transcribed_calls
 
20
  split: None
21
  args: default
22
  metrics:
23
+ - type: wer
 
24
  value: 1.0
25
+ name: Wer
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
vocab.json CHANGED
@@ -1,47 +1,47 @@
1
  {
2
  "[PAD]": 44,
3
  "[UNK]": 43,
4
- "a": 20,
5
- "b": 10,
6
- "d": 27,
7
- "e": 3,
8
- "f": 40,
9
- "h": 15,
10
- "i": 7,
11
- "j": 33,
12
- "k": 9,
13
- "l": 42,
14
- "m": 13,
15
- "n": 31,
16
- "o": 36,
17
- "p": 25,
18
- "s": 34,
19
- "t": 1,
20
- "u": 8,
21
- "v": 38,
22
- "w": 4,
23
- "z": 28,
24
  "|": 17,
25
- "æ": 2,
26
- "ð": 18,
27
- "ŋ": 19,
28
- "ɐ": 12,
29
- "ɑ": 24,
30
- "ɔ": 11,
31
- "ə": 16,
32
- "ɚ": 14,
33
- "ɛ": 6,
34
- "ɜ": 37,
35
- "ɡ": 22,
36
- "ɣ": 39,
37
- "ɪ": 41,
38
- "ɹ": 26,
39
- "ɾ": 35,
40
- "ʃ": 0,
41
- "ʊ": 29,
42
- "ʌ": 5,
43
- "ʒ": 30,
44
- "ː": 21,
45
- "θ": 23,
46
- "ᵻ": 32
47
  }
 
1
  {
2
  "[PAD]": 44,
3
  "[UNK]": 43,
4
+ "a": 9,
5
+ "b": 3,
6
+ "d": 14,
7
+ "e": 0,
8
+ "f": 23,
9
+ "h": 29,
10
+ "i": 26,
11
+ "j": 42,
12
+ "k": 41,
13
+ "l": 7,
14
+ "m": 27,
15
+ "n": 37,
16
+ "o": 19,
17
+ "p": 4,
18
+ "s": 28,
19
+ "t": 24,
20
+ "u": 5,
21
+ "v": 31,
22
+ "w": 40,
23
+ "z": 11,
24
  "|": 17,
25
+ "æ": 39,
26
+ "ð": 25,
27
+ "ŋ": 33,
28
+ "ɐ": 16,
29
+ "ɑ": 10,
30
+ "ɔ": 15,
31
+ "ə": 22,
32
+ "ɚ": 13,
33
+ "ɛ": 32,
34
+ "ɜ": 12,
35
+ "ɡ": 1,
36
+ "ɣ": 30,
37
+ "ɪ": 36,
38
+ "ɹ": 20,
39
+ "ɾ": 21,
40
+ "ʃ": 8,
41
+ "ʊ": 35,
42
+ "ʌ": 6,
43
+ "ʒ": 2,
44
+ "ː": 38,
45
+ "θ": 34,
46
+ "ᵻ": 18
47
  }