Hugging Face's logo

Lasion
/
wav2vec2-common-voice-17_0_vi

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Lasion commited on
Commit
2aa88be
•
1 Parent(s): 137933f

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +4 -2
  2. tokenizer_config.json +22 -6
  3. vocab.json +109 -95
added_tokens.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
- "</s>": 97,
3
- "<s>": 96
 
 
4
  }
 
1
  {
2
+ "</s>": 111,
3
+ "<s>": 110,
4
+ "[PAD]": 113,
5
+ "[UNK]": 112
6
  }
tokenizer_config.json CHANGED
@@ -1,22 +1,22 @@
1
  {
2
  "added_tokens_decoder": {
3
- "94": {
4
- "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
- "95": {
12
- "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
16
  "single_word": false,
17
  "special": false
18
  },
19
- "96": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,13 +24,29 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "97": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  }
35
  },
36
  "bos_token": "<s>",
 
1
  {
2
  "added_tokens_decoder": {
3
+ "108": {
4
+ "content": "<unk>",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "109": {
12
+ "content": "<pad>",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "110": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "111": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
+ },
35
+ "112": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "113": {
44
+ "content": "[PAD]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
  }
51
  },
52
  "bos_token": "<s>",
vocab.json CHANGED
@@ -1,98 +1,112 @@
1
  {
2
- "[PAD]": 95,
3
- "[UNK]": 94,
4
- "a": 73,
5
- "b": 88,
6
- "c": 70,
7
- "d": 3,
8
- "e": 71,
9
- "f": 47,
10
- "g": 28,
11
- "h": 75,
12
- "i": 24,
13
- "j": 80,
14
- "k": 39,
15
- "l": 16,
16
- "m": 22,
17
- "n": 40,
18
- "o": 32,
19
- "p": 83,
20
- "q": 54,
21
- "r": 0,
22
- "s": 61,
23
- "t": 66,
24
- "u": 52,
25
- "v": 34,
26
- "w": 84,
27
- "x": 9,
28
- "y": 92,
29
- "z": 35,
30
- "|": 79,
31
- "à": 41,
32
- "á": 14,
33
- "â": 27,
34
- "ã": 76,
35
- "è": 74,
36
- "é": 87,
37
- "ê": 81,
38
- "ì": 53,
39
- "í": 69,
40
- "ò": 5,
41
- "ó": 31,
42
- "ô": 2,
43
- "õ": 19,
44
- "ù": 44,
45
- "ú": 25,
46
- "ý": 7,
47
- "ă": 60,
48
- "đ": 12,
49
- "ĩ": 90,
50
- "ũ": 42,
51
- "ơ": 10,
52
- "ư": 6,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  "ạ": 50,
54
- "ả": 93,
55
- "ấ": 38,
56
- "ầ": 51,
57
- "ẩ": 33,
58
- "ẫ": 43,
59
- "ậ": 85,
60
- "ắ": 45,
61
- "ằ": 11,
62
- "ẳ": 17,
63
- "ẵ": 89,
64
- "ặ": 26,
65
- "ẹ": 57,
66
- "ẻ": 49,
67
- "ẽ": 23,
68
- "ế": 4,
69
- "ề": 37,
70
- "ể": 1,
71
- "ễ": 62,
72
- "ệ": 20,
73
- "ỉ": 91,
74
- "ị": 86,
75
- "ọ": 30,
76
- "ỏ": 58,
77
- "ố": 15,
78
- "ồ": 8,
79
- "ổ": 18,
80
- "ỗ": 46,
81
- "ộ": 82,
82
- "ớ": 64,
83
- "ờ": 68,
84
- "ở": 78,
85
- "ỡ": 56,
86
- "ợ": 48,
87
- "ụ": 13,
88
- "ủ": 21,
89
- "ứ": 65,
90
- "ừ": 67,
91
- "ử": 77,
92
- "ữ": 55,
93
- "ự": 72,
94
- "ỳ": 29,
95
- "ỵ": 63,
96
- "ỷ": 36,
97
- "ỹ": 59
98
  }
 
1
  {
2
+ "0": 63,
3
+ "1": 94,
4
+ "2": 55,
5
+ "3": 4,
6
+ "4": 34,
7
+ "5": 107,
8
+ "6": 1,
9
+ "7": 11,
10
+ "8": 43,
11
+ "9": 51,
12
+ "<pad>": 109,
13
+ "<unk>": 108,
14
+ "a": 17,
15
+ "b": 36,
16
+ "c": 49,
17
+ "d": 44,
18
+ "e": 65,
19
+ "f": 77,
20
+ "g": 58,
21
+ "h": 71,
22
+ "i": 57,
23
+ "j": 22,
24
+ "k": 96,
25
+ "l": 18,
26
+ "m": 67,
27
+ "n": 26,
28
+ "o": 105,
29
+ "p": 98,
30
+ "q": 20,
31
+ "r": 47,
32
+ "s": 39,
33
+ "t": 56,
34
+ "u": 31,
35
+ "v": 15,
36
+ "w": 35,
37
+ "x": 81,
38
+ "y": 32,
39
+ "z": 87,
40
+ "|": 46,
41
+ "à": 24,
42
+ "á": 62,
43
+ "â": 72,
44
+ "ã": 83,
45
+ "è": 90,
46
+ "é": 27,
47
+ "ê": 12,
48
+ "ì": 40,
49
+ "í": 3,
50
+ "ò": 92,
51
+ "ó": 82,
52
+ "ô": 30,
53
+ "õ": 10,
54
+ "ù": 53,
55
+ "ú": 73,
56
+ "ý": 6,
57
+ "ă": 104,
58
+ "đ": 89,
59
+ "ĩ": 70,
60
+ "ũ": 48,
61
+ "ơ": 95,
62
+ "ư": 106,
63
+ "̀": 61,
64
+ "́": 59,
65
+ "̣": 86,
66
+ "у": 29,
67
  "ạ": 50,
68
+ "ả": 88,
69
+ "ấ": 99,
70
+ "ầ": 41,
71
+ "ẩ": 7,
72
+ "ẫ": 97,
73
+ "ậ": 64,
74
+ "ắ": 79,
75
+ "ằ": 33,
76
+ "ẳ": 68,
77
+ "ẵ": 93,
78
+ "ặ": 76,
79
+ "ẹ": 103,
80
+ "ẻ": 0,
81
+ "ẽ": 100,
82
+ "ế": 52,
83
+ "ề": 9,
84
+ "ể": 45,
85
+ "ễ": 38,
86
+ "ệ": 37,
87
+ "ỉ": 101,
88
+ "ị": 85,
89
+ "ọ": 74,
90
+ "ỏ": 14,
91
+ "ố": 23,
92
+ "ồ": 75,
93
+ "ổ": 84,
94
+ "ỗ": 25,
95
+ "ộ": 66,
96
+ "ớ": 102,
97
+ "ờ": 21,
98
+ "ở": 8,
99
+ "ỡ": 54,
100
+ "ợ": 69,
101
+ "ụ": 2,
102
+ "ủ": 28,
103
+ "ứ": 13,
104
+ "ừ": 91,
105
+ "ử": 60,
106
+ "ữ": 78,
107
+ "ự": 19,
108
+ "ỳ": 80,
109
+ "ỵ": 42,
110
+ "ỷ": 16,
111
+ "ỹ": 5
112
  }