Hugging Face's logo

doof-ferb
/
whisper-tiny-vi

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
10 datasets
Vietnamese
whisper
Eval Results
Inference Endpoints
Model card Files Metrics Community
whisper-tiny-vi
File size: 2,399 Bytes 
4deb04e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
 
{
	"alignment_heads": [
		[2, 2],
		[3, 0],
		[3, 2],
		[3, 3],
		[3, 4],
		[3, 5]
	],
	"begin_suppress_tokens": [220, 50257],
	"bos_token_id": 50257,
	"decoder_start_token_id": 50258,
	"eos_token_id": 50257,
	"is_multilingual": true,
	"lang_to_id": {
		"<|af|>": 50327,
		"<|am|>": 50334,
		"<|ar|>": 50272,
		"<|as|>": 50350,
		"<|az|>": 50304,
		"<|ba|>": 50355,
		"<|be|>": 50330,
		"<|bg|>": 50292,
		"<|bn|>": 50302,
		"<|bo|>": 50347,
		"<|br|>": 50309,
		"<|bs|>": 50315,
		"<|ca|>": 50270,
		"<|cs|>": 50283,
		"<|cy|>": 50297,
		"<|da|>": 50285,
		"<|de|>": 50261,
		"<|el|>": 50281,
		"<|en|>": 50259,
		"<|es|>": 50262,
		"<|et|>": 50307,
		"<|eu|>": 50310,
		"<|fa|>": 50300,
		"<|fi|>": 50277,
		"<|fo|>": 50338,
		"<|fr|>": 50265,
		"<|gl|>": 50319,
		"<|gu|>": 50333,
		"<|haw|>": 50352,
		"<|ha|>": 50354,
		"<|he|>": 50279,
		"<|hi|>": 50276,
		"<|hr|>": 50291,
		"<|ht|>": 50339,
		"<|hu|>": 50286,
		"<|hy|>": 50312,
		"<|id|>": 50275,
		"<|is|>": 50311,
		"<|it|>": 50274,
		"<|ja|>": 50266,
		"<|jw|>": 50356,
		"<|ka|>": 50329,
		"<|kk|>": 50316,
		"<|km|>": 50323,
		"<|kn|>": 50306,
		"<|ko|>": 50264,
		"<|la|>": 50294,
		"<|lb|>": 50345,
		"<|ln|>": 50353,
		"<|lo|>": 50336,
		"<|lt|>": 50293,
		"<|lv|>": 50301,
		"<|mg|>": 50349,
		"<|mi|>": 50295,
		"<|mk|>": 50308,
		"<|ml|>": 50296,
		"<|mn|>": 50314,
		"<|mr|>": 50320,
		"<|ms|>": 50282,
		"<|mt|>": 50343,
		"<|my|>": 50346,
		"<|ne|>": 50313,
		"<|nl|>": 50271,
		"<|nn|>": 50342,
		"<|no|>": 50288,
		"<|oc|>": 50328,
		"<|pa|>": 50321,
		"<|pl|>": 50269,
		"<|ps|>": 50340,
		"<|pt|>": 50267,
		"<|ro|>": 50284,
		"<|ru|>": 50263,
		"<|sa|>": 50344,
		"<|sd|>": 50332,
		"<|si|>": 50322,
		"<|sk|>": 50298,
		"<|sl|>": 50305,
		"<|sn|>": 50324,
		"<|so|>": 50326,
		"<|sq|>": 50317,
		"<|sr|>": 50303,
		"<|su|>": 50357,
		"<|sv|>": 50273,
		"<|sw|>": 50318,
		"<|ta|>": 50287,
		"<|te|>": 50299,
		"<|tg|>": 50331,
		"<|th|>": 50289,
		"<|tk|>": 50341,
		"<|tl|>": 50348,
		"<|tr|>": 50268,
		"<|tt|>": 50351,
		"<|uk|>": 50280,
		"<|ur|>": 50290,
		"<|uz|>": 50337,
		"<|vi|>": 50278,
		"<|yi|>": 50335,
		"<|yo|>": 50325,
		"<|zh|>": 50260
	},
	"max_initial_timestamp_index": 50,
	"max_length": 448,
	"no_timestamps_token_id": 50363,
	"pad_token_id": 50257,
	"prev_sot_token_id": 50361,
	"return_timestamps": false,
	"suppress_tokens": [],
	"task_to_id": {
		"transcribe": 50359,
		"translate": 50358
	}
}