Hugging Face's logo

ntxcong
/
hubert-base-common-voice-vi-demo

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ntxcong commited on
Commit
deae9a3
•
1 Parent(s): b014f05

Upload tokenizer

Browse files
Files changed (1) hide show
  1. vocab.json +94 -94
vocab.json CHANGED
@@ -1,99 +1,99 @@
1
  {
2
- "'": 1,
3
  "[PAD]": 96,
4
  "[UNK]": 95,
5
- "a": 61,
6
- "b": 54,
7
- "c": 37,
8
- "d": 42,
9
- "e": 26,
10
- "f": 47,
11
- "g": 91,
12
- "h": 70,
13
- "i": 46,
14
- "j": 39,
15
- "k": 78,
16
- "l": 89,
17
- "m": 19,
18
- "n": 38,
19
- "o": 35,
20
  "p": 68,
21
- "q": 55,
22
- "r": 66,
23
- "s": 72,
24
- "t": 18,
25
- "u": 62,
26
- "v": 73,
27
- "w": 79,
28
- "x": 40,
29
- "y": 29,
30
- "z": 58,
31
- "|": 24,
32
- "à": 53,
33
- "á": 86,
34
- "â": 80,
35
- "ã": 8,
36
- "è": 41,
37
- "é": 7,
38
- "ê": 82,
39
- "ì": 5,
40
- "í": 92,
41
- "ò": 94,
42
- "ó": 93,
43
- "ô": 49,
44
- "õ": 76,
45
- "ù": 11,
46
- "ú": 20,
47
- "ý": 63,
48
- "ă": 44,
49
- "đ": 48,
50
- "ĩ": 52,
51
- "ũ": 45,
52
- "ơ": 33,
53
- "ư": 74,
54
- "ạ": 21,
55
- "ả": 77,
56
- "ấ": 13,
57
- "ầ": 64,
58
- "ẩ": 81,
59
- "ẫ": 9,
60
- "ậ": 83,
61
- "ắ": 27,
62
- "ằ": 31,
63
- "ẳ": 6,
64
- "ẵ": 87,
65
- "ặ": 85,
66
- "ẹ": 67,
67
- "ẻ": 75,
68
- "ẽ": 36,
69
- "ế": 28,
70
- "ề": 12,
71
- "ể": 23,
72
- "ễ": 51,
73
- "ệ": 2,
74
- "ỉ": 59,
75
- "ị": 90,
76
- "ọ": 57,
77
- "ỏ": 25,
78
- "ố": 84,
79
- "ồ": 32,
80
- "ổ": 88,
81
- "ỗ": 3,
82
- "ộ": 30,
83
- "ớ": 71,
84
- "ờ": 10,
85
- "ở": 69,
86
- "ỡ": 34,
87
- "ợ": 16,
88
- "ụ": 43,
89
- "ủ": 22,
90
- "ứ": 65,
91
- "ừ": 15,
92
- "ử": 0,
93
- "ữ": 56,
94
- "ự": 4,
95
- "ỳ": 17,
96
- "ỵ": 50,
97
- "ỷ": 60,
98
- "ỹ": 14
99
  }
 
1
  {
2
+ "'": 71,
3
  "[PAD]": 96,
4
  "[UNK]": 95,
5
+ "a": 63,
6
+ "b": 5,
7
+ "c": 25,
8
+ "d": 30,
9
+ "e": 56,
10
+ "f": 18,
11
+ "g": 73,
12
+ "h": 8,
13
+ "i": 57,
14
+ "j": 83,
15
+ "k": 44,
16
+ "l": 48,
17
+ "m": 38,
18
+ "n": 69,
19
+ "o": 92,
20
  "p": 68,
21
+ "q": 81,
22
+ "r": 23,
23
+ "s": 82,
24
+ "t": 29,
25
+ "u": 7,
26
+ "v": 52,
27
+ "w": 32,
28
+ "x": 6,
29
+ "y": 34,
30
+ "z": 94,
31
+ "|": 37,
32
+ "à": 26,
33
+ "á": 66,
34
+ "â": 45,
35
+ "ã": 12,
36
+ "è": 24,
37
+ "é": 41,
38
+ "ê": 3,
39
+ "ì": 13,
40
+ "í": 20,
41
+ "ò": 15,
42
+ "ó": 76,
43
+ "ô": 50,
44
+ "õ": 14,
45
+ "ù": 9,
46
+ "ú": 35,
47
+ "ý": 42,
48
+ "ă": 61,
49
+ "đ": 60,
50
+ "ĩ": 22,
51
+ "ũ": 58,
52
+ "ơ": 21,
53
+ "ư": 75,
54
+ "ạ": 85,
55
+ "ả": 53,
56
+ "ấ": 46,
57
+ "ầ": 86,
58
+ "ẩ": 80,
59
+ "ẫ": 64,
60
+ "ậ": 19,
61
+ "ắ": 33,
62
+ "ằ": 47,
63
+ "ẳ": 79,
64
+ "ẵ": 77,
65
+ "ặ": 0,
66
+ "ẹ": 49,
67
+ "ẻ": 91,
68
+ "ẽ": 51,
69
+ "ế": 11,
70
+ "ề": 87,
71
+ "ể": 90,
72
+ "ễ": 88,
73
+ "ệ": 1,
74
+ "ỉ": 78,
75
+ "ị": 28,
76
+ "ọ": 10,
77
+ "ỏ": 59,
78
+ "ố": 62,
79
+ "ồ": 16,
80
+ "ổ": 43,
81
+ "ỗ": 55,
82
+ "ộ": 2,
83
+ "ớ": 4,
84
+ "ờ": 27,
85
+ "ở": 65,
86
+ "ỡ": 89,
87
+ "ợ": 74,
88
+ "ụ": 36,
89
+ "ủ": 17,
90
+ "ứ": 54,
91
+ "ừ": 70,
92
+ "ử": 93,
93
+ "ữ": 31,
94
+ "ự": 67,
95
+ "ỳ": 39,
96
+ "ỵ": 40,
97
+ "ỷ": 72,
98
+ "ỹ": 84
99
  }