gweltou commited on
Commit
6799feb
1 Parent(s): 0775e97

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +4 -4
  2. added_tokens.json +2 -2
  3. tokenizer_config.json +4 -4
  4. vocab.json +49 -48
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: cc-by-nc-4.0
3
- base_model: utter-project/mHuBERT-147
4
  tags:
5
  - generated_from_trainer
 
6
  datasets:
7
  - common_voice_15_0
8
  metrics:
@@ -11,8 +11,8 @@ model-index:
11
  - name: mHuBERT-147-br
12
  results:
13
  - task:
14
- name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
 
16
  dataset:
17
  name: common_voice_15_0
18
  type: common_voice_15_0
@@ -20,9 +20,9 @@ model-index:
20
  split: None
21
  args: br
22
  metrics:
23
- - name: Wer
24
- type: wer
25
  value: 53.76572908956329
 
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
1
  ---
2
  license: cc-by-nc-4.0
 
3
  tags:
4
  - generated_from_trainer
5
+ base_model: utter-project/mHuBERT-147
6
  datasets:
7
  - common_voice_15_0
8
  metrics:
 
11
  - name: mHuBERT-147-br
12
  results:
13
  - task:
 
14
  type: automatic-speech-recognition
15
+ name: Automatic Speech Recognition
16
  dataset:
17
  name: common_voice_15_0
18
  type: common_voice_15_0
 
20
  split: None
21
  args: br
22
  metrics:
23
+ - type: wer
 
24
  value: 53.76572908956329
25
+ name: Wer
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 49,
3
- "<s>": 48
4
  }
 
1
  {
2
+ "</s>": 50,
3
+ "<s>": 49
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "46": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "47": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "48": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "49": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "47": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "48": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "49": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "50": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,50 +1,51 @@
1
  {
2
- "'": 24,
3
- "3": 37,
4
- "[PAD]": 47,
5
- "[UNK]": 46,
6
- "a": 33,
7
- "b": 17,
8
- "c": 12,
9
- "d": 4,
10
- "e": 11,
11
- "f": 34,
12
- "g": 9,
13
- "h": 42,
14
- "i": 31,
15
- "j": 6,
16
- "k": 44,
17
- "l": 14,
18
- "m": 27,
19
- "n": 2,
20
- "o": 23,
21
- "p": 35,
22
- "q": 3,
23
- "r": 7,
24
- "s": 18,
25
- "t": 13,
26
- "u": 16,
27
- "v": 28,
28
- "w": 15,
29
- "x": 43,
30
- "y": 0,
31
- "z": 26,
32
- "|": 8,
33
- "à": 21,
34
- "á": 5,
35
- "â": 20,
36
- "ã": 22,
37
- "ç": 41,
38
- "è": 32,
39
- "é": 36,
40
- "ê": 25,
41
- "ë": 40,
42
- "ñ": 29,
43
- "ô": 19,
44
- "ö": 10,
45
- "ø": 30,
46
- "ù": 1,
47
- "û": 45,
48
- "ü": 38,
49
- "ı": 39
 
50
  }
 
1
  {
2
+ "'": 31,
3
+ "3": 15,
4
+ "X": 25,
5
+ "[PAD]": 48,
6
+ "[UNK]": 47,
7
+ "a": 14,
8
+ "b": 23,
9
+ "c": 5,
10
+ "d": 27,
11
+ "e": 24,
12
+ "f": 16,
13
+ "g": 29,
14
+ "h": 1,
15
+ "i": 45,
16
+ "j": 35,
17
+ "k": 9,
18
+ "l": 36,
19
+ "m": 22,
20
+ "n": 42,
21
+ "o": 17,
22
+ "p": 21,
23
+ "q": 28,
24
+ "r": 10,
25
+ "s": 46,
26
+ "t": 37,
27
+ "u": 0,
28
+ "v": 34,
29
+ "w": 12,
30
+ "x": 8,
31
+ "y": 43,
32
+ "z": 33,
33
+ "|": 26,
34
+ "à": 11,
35
+ "á": 19,
36
+ "â": 39,
37
+ "ã": 30,
38
+ "ç": 40,
39
+ "è": 38,
40
+ "é": 32,
41
+ "ê": 4,
42
+ "ë": 41,
43
+ "ñ": 13,
44
+ "ô": 18,
45
+ "ö": 3,
46
+ "ø": 7,
47
+ "ù": 44,
48
+ "û": 6,
49
+ "ü": 2,
50
+ "ı": 20
51
  }