Hugging Face's logo

dolphinnlp
/
wav2vec2vncskh

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
infi commited on
Commit
cb7d662
·
1 Parent(s): e591024

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +3 -1
  2. tokenizer_config.json +17 -2
  3. vocab.json +106 -106
added_tokens.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
  "</s>": 107,
3
- "[PAD]": 106
 
 
4
  }
 
1
  {
2
  "</s>": 107,
3
+ "<s>": 106,
4
+ "[PAD]": 105,
5
+ "[UNK]": 104
6
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,14 @@
1
  {
2
  "added_tokens_decoder": {
3
- "106": {
 
 
 
 
 
 
 
 
4
  "content": "[PAD]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,6 +16,14 @@
8
  "single_word": false,
9
  "special": false
10
  },
 
 
 
 
 
 
 
 
11
  "107": {
12
  "content": "</s>",
13
  "lstrip": false,
@@ -23,7 +39,6 @@
23
  "eos_token": "</s>",
24
  "model_max_length": 1000000000000000019884624838656,
25
  "pad_token": "[PAD]",
26
- "processor_class": "Wav2Vec2Processor",
27
  "replace_word_delimiter_char": " ",
28
  "target_lang": null,
29
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
1
  {
2
  "added_tokens_decoder": {
3
+ "104": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "105": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "106": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
  "107": {
28
  "content": "</s>",
29
  "lstrip": 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
@@ -1,108 +1,108 @@
1
  {
2
- "%": 17,
3
- ".": 88,
4
- "0": 8,
5
- "1": 92,
6
- "2": 89,
7
- "3": 2,
8
- "4": 42,
9
- "5": 61,
10
- "6": 105,
11
- "7": 48,
12
- "8": 77,
13
- "<": 1,
14
- ">": 1,
15
- "[PAD]": 106,
16
- "[UNK]": 106,
17
- "a": 64,
18
- "b": 53,
19
- "c": 90,
20
- "d": 32,
21
- "e": 20,
22
- "f": 55,
23
- "g": 62,
24
- "h": 80,
25
- "i": 95,
26
- "k": 25,
27
- "l": 30,
28
- "m": 27,
29
- "n": 18,
30
- "o": 21,
31
- "p": 70,
32
- "q": 101,
33
- "r": 28,
34
- "s": 102,
35
- "t": 69,
36
- "u": 10,
37
- "v": 34,
38
- "w": 37,
39
- "x": 50,
40
- "y": 13,
41
- "z": 76,
42
- "à": 31,
43
- "á": 73,
44
- "â": 47,
45
- "ã": 71,
46
- "è": 12,
47
- "é": 26,
48
- "ê": 99,
49
- "ì": 9,
50
- "í": 63,
51
- "ò": 97,
52
- "ó": 22,
53
- "ô": 57,
54
- "õ": 91,
55
- "ù": 23,
56
- "ú": 46,
57
- "ý": 60,
58
- "ă": 96,
59
- "đ": 35,
60
- "ĩ": 14,
61
- "ũ": 81,
62
- "ơ": 11,
63
- "ư": 98,
64
- "ạ": 6,
65
- "ả": 52,
66
- "ấ": 67,
67
- "ầ": 54,
68
- "ẩ": 82,
69
- "ẫ": 65,
70
- "ậ": 106,
71
- "ắ": 40,
72
- "ằ": 86,
73
- "ẳ": 15,
74
- "ẵ": 45,
75
- "ặ": 103,
76
- "ẹ": 7,
77
- "ẻ": 58,
78
- "ẽ": 59,
79
- "ế": 16,
80
- "ề": 38,
81
- "ể": 78,
82
- "ễ": 100,
83
- "ệ": 29,
84
- "ỉ": 75,
85
- "ị": 72,
86
- "ọ": 0,
87
- "ỏ": 68,
88
- "ố": 41,
89
- "ồ": 4,
90
- "ổ": 85,
91
- "ỗ": 74,
92
- "ộ": 84,
93
- "ớ": 24,
94
- "ờ": 43,
95
- "ở": 3,
96
- "ỡ": 94,
97
- "ợ": 5,
98
- "ụ": 19,
99
- "ủ": 87,
100
- "ứ": 33,
101
- "ừ": 51,
102
- "ử": 104,
103
- "ữ": 66,
104
- "ự": 79,
105
- "ỳ": 83,
106
- "ỷ": 56,
107
- "ỹ": 39
108
  }
 
1
  {
2
+ "%": 46,
3
+ ",": 7,
4
+ ".": 53,
5
+ "0": 87,
6
+ "1": 2,
7
+ "2": 79,
8
+ "3": 60,
9
+ "4": 78,
10
+ "5": 82,
11
+ "6": 72,
12
+ "7": 3,
13
+ "8": 33,
14
+ "9": 32,
15
+ "[PAD]": 105,
16
+ "[UNK]": 104,
17
+ "a": 73,
18
+ "b": 90,
19
+ "c": 57,
20
+ "d": 94,
21
+ "e": 89,
22
+ "f": 21,
23
+ "g": 28,
24
+ "h": 96,
25
+ "i": 86,
26
+ "k": 13,
27
+ "l": 62,
28
+ "m": 12,
29
+ "n": 104,
30
+ "o": 81,
31
+ "p": 100,
32
+ "q": 50,
33
+ "r": 37,
34
+ "s": 16,
35
+ "t": 102,
36
+ "u": 69,
37
+ "v": 70,
38
+ "w": 26,
39
+ "x": 40,
40
+ "y": 20,
41
+ "z": 44,
42
+ "à": 27,
43
+ "á": 66,
44
+ "â": 5,
45
+ "ã": 19,
46
+ "è": 85,
47
+ "é": 41,
48
+ "ê": 92,
49
+ "ì": 95,
50
+ "í": 38,
51
+ "ò": 63,
52
+ "ó": 4,
53
+ "ô": 88,
54
+ "õ": 75,
55
+ "ù": 11,
56
+ "ú": 91,
57
+ "ý": 98,
58
+ "ă": 76,
59
+ "đ": 77,
60
+ "ĩ": 45,
61
+ "ũ": 35,
62
+ "ơ": 10,
63
+ "ư": 43,
64
+ "ạ": 68,
65
+ "ả": 34,
66
+ "ấ": 71,
67
+ "ầ": 80,
68
+ "ẩ": 58,
69
+ "ẫ": 8,
70
+ "ậ": 97,
71
+ "ắ": 48,
72
+ "ằ": 106,
73
+ "ẳ": 22,
74
+ "ẵ": 29,
75
+ "ặ": 42,
76
+ "ẹ": 107,
77
+ "ẻ": 31,
78
+ "ẽ": 103,
79
+ "ế": 15,
80
+ "ề": 59,
81
+ "ể": 23,
82
+ "ễ": 93,
83
+ "ệ": 36,
84
+ "ỉ": 52,
85
+ "ị": 18,
86
+ "ọ": 83,
87
+ "ỏ": 39,
88
+ "ố": 99,
89
+ "ồ": 101,
90
+ "ổ": 56,
91
+ "ỗ": 61,
92
+ "ộ": 51,
93
+ "ớ": 67,
94
+ "ờ": 9,
95
+ "ở": 30,
96
+ "ỡ": 55,
97
+ "ợ": 54,
98
+ "ụ": 47,
99
+ "ủ": 1,
100
+ "ứ": 105,
101
+ "ừ": 64,
102
+ "ử": 74,
103
+ "ữ": 25,
104
+ "ự": 24,
105
+ "ỳ": 6,
106
+ "ỷ": 84,
107
+ "ỹ": 65
108
  }