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
62a84b7
•
1 Parent(s): 3198ab4

Upload tokenizer

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