Bajiyo commited on
Commit
a053dcb
1 Parent(s): 8134751

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +7 -7
  2. added_tokens.json +2 -2
  3. tokenizer_config.json +4 -5
  4. vocab.json +97 -78
README.md CHANGED
@@ -1,19 +1,19 @@
1
  ---
2
- library_name: transformers
3
- license: mit
4
  base_model: facebook/w2v-bert-2.0
5
- tags:
6
- - generated_from_trainer
7
  datasets:
8
  - common_voice_17_0
 
 
9
  metrics:
10
  - wer
 
 
11
  model-index:
12
  - name: w2v-bert-2_6_datasets
13
  results:
14
  - task:
15
- name: Automatic Speech Recognition
16
  type: automatic-speech-recognition
 
17
  dataset:
18
  name: common_voice_17_0
19
  type: common_voice_17_0
@@ -21,9 +21,9 @@ model-index:
21
  split: validation
22
  args: ml
23
  metrics:
24
- - name: Wer
25
- type: wer
26
  value: 0.43922053819981444
 
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
1
  ---
 
 
2
  base_model: facebook/w2v-bert-2.0
 
 
3
  datasets:
4
  - common_voice_17_0
5
+ library_name: transformers
6
+ license: mit
7
  metrics:
8
  - wer
9
+ tags:
10
+ - generated_from_trainer
11
  model-index:
12
  - name: w2v-bert-2_6_datasets
13
  results:
14
  - task:
 
15
  type: automatic-speech-recognition
16
+ name: Automatic Speech Recognition
17
  dataset:
18
  name: common_voice_17_0
19
  type: common_voice_17_0
 
21
  split: validation
22
  args: ml
23
  metrics:
24
+ - type: wer
 
25
  value: 0.43922053819981444
26
+ name: Wer
27
  ---
28
 
29
  <!-- 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>": 80,
3
- "<s>": 79
4
  }
 
1
  {
2
+ "</s>": 99,
3
+ "<s>": 98
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "77": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "78": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "79": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "80": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
@@ -39,7 +39,6 @@
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
42
- "processor_class": "Wav2Vec2BertProcessor",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
1
  {
2
  "added_tokens_decoder": {
3
+ "96": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "97": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "98": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "99": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
 
42
  "replace_word_delimiter_char": " ",
43
  "target_lang": null,
44
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
vocab.json CHANGED
@@ -1,81 +1,100 @@
1
  {
2
- "[PAD]": 78,
3
- "[UNK]": 77,
4
- "_": 1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "|": 0,
6
- "": 2,
7
- "": 3,
8
- "": 4,
9
- "": 5,
10
- "": 6,
11
- "": 7,
12
- "": 8,
13
- "": 9,
14
- "": 10,
15
- "": 11,
16
- "": 12,
17
- "": 13,
18
- "": 14,
19
- "": 15,
20
- "": 16,
21
- "": 17,
22
- "": 18,
23
- "": 19,
24
- "": 20,
25
- "": 21,
26
- "": 22,
27
- "": 23,
28
- "": 24,
29
- "": 25,
30
- "": 26,
31
- "": 27,
32
- "": 28,
33
- "": 29,
34
- "": 30,
35
- "": 31,
36
- "": 32,
37
- "": 33,
38
- "": 34,
39
- "": 35,
40
- "": 36,
41
- "": 37,
42
- "": 38,
43
- "": 39,
44
- "": 40,
45
- "": 41,
46
- "": 42,
47
- "": 43,
48
- "": 44,
49
- "": 45,
50
- "": 46,
51
- "": 47,
52
- "": 48,
53
- "": 49,
54
- "": 50,
55
- "": 51,
56
- "": 52,
57
- "": 53,
58
- "ി": 54,
59
- "": 55,
60
- "": 56,
61
- "": 57,
62
- "": 58,
63
- "": 59,
64
- "": 60,
65
- "": 61,
66
- "": 62,
67
- "": 63,
68
- "": 64,
69
- "": 65,
70
- "": 66,
71
- "": 67,
72
- "": 68,
73
- "": 69,
74
- "": 70,
75
- "": 71,
76
- "": 72,
77
- "ൿ": 73,
78
- "": 74,
79
- "": 75,
80
- "": 76
 
 
 
81
  }
 
1
  {
2
+ "$": 1,
3
+ "&": 2,
4
+ "+": 3,
5
+ "/": 4,
6
+ "0": 5,
7
+ "1": 6,
8
+ "2": 7,
9
+ "3": 8,
10
+ "4": 9,
11
+ "5": 10,
12
+ "6": 11,
13
+ "7": 12,
14
+ "8": 13,
15
+ "9": 14,
16
+ "[": 15,
17
+ "[PAD]": 97,
18
+ "[UNK]": 96,
19
+ "]": 16,
20
+ "_": 17,
21
  "|": 0,
22
+ "~": 18,
23
+ "°": 19,
24
+ "": 20,
25
+ "": 21,
26
+ "": 22,
27
+ "": 23,
28
+ "": 24,
29
+ "": 25,
30
+ "": 26,
31
+ "": 27,
32
+ "": 28,
33
+ "": 29,
34
+ "": 30,
35
+ "": 31,
36
+ "": 32,
37
+ "": 33,
38
+ "": 34,
39
+ "": 35,
40
+ "": 36,
41
+ "": 37,
42
+ "": 38,
43
+ "": 39,
44
+ "": 40,
45
+ "": 41,
46
+ "": 42,
47
+ "": 43,
48
+ "": 44,
49
+ "": 45,
50
+ "": 46,
51
+ "": 47,
52
+ "": 48,
53
+ "": 49,
54
+ "": 50,
55
+ "": 51,
56
+ "": 52,
57
+ "": 53,
58
+ "": 54,
59
+ "": 55,
60
+ "": 56,
61
+ "": 57,
62
+ "": 58,
63
+ "": 59,
64
+ "": 60,
65
+ "": 61,
66
+ "": 62,
67
+ "": 63,
68
+ "": 64,
69
+ "": 65,
70
+ "": 66,
71
+ "": 67,
72
+ "": 68,
73
+ "": 69,
74
+ "": 70,
75
+ "": 71,
76
+ "ി": 72,
77
+ "": 73,
78
+ "": 74,
79
+ "": 75,
80
+ "": 76,
81
+ "": 77,
82
+ "": 78,
83
+ "": 79,
84
+ "": 80,
85
+ "": 81,
86
+ "": 82,
87
+ "": 83,
88
+ "": 84,
89
+ "": 85,
90
+ "": 86,
91
+ "": 87,
92
+ "": 88,
93
+ "": 89,
94
+ "": 90,
95
+ "ൿ": 91,
96
+ "": 92,
97
+ "‍": 93,
98
+ "–": 94,
99
+ "’": 95
100
  }