Hugging Face's logo

hezarai
/
whisper-small-fa

Automatic Speech Recognition
Hezar
Persian
Model card Files Community
whisper-small-fa
File size: 1,855 Bytes 
72c619d
 
021ecaa
72c619d
 
 
 
 
 
 
98680b6
9bee4db
72c619d
9bee4db
021ecaa
9bee4db
 
 
72c619d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
021ecaa
72c619d
 
 
 
9bee4db
 
 
72c619d
 
 
593e864
72c619d
 
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
 
name: whisper_bpe_tokenizer
config_type: preprocessor
max_length: 448
truncation_strategy: longest_first
truncation_direction: right
stride: 0
padding_strategy: longest
padding_direction: right
pad_to_multiple_of: 0
pad_token_type_id: 0
bos_token: <|startoftranscript|>
eos_token: <|endoftext|>
unk_token: <|endoftext|>
sep_token: <sep>
pad_token: <|endoftext|>
cls_token: <cls>
mask_token: <mask>
additional_special_tokens:
- <|endoftext|>
- <|endoftext|>
- <|startoftranscript|>
- <|en|>
- <|zh|>
- <|de|>
- <|es|>
- <|ru|>
- <|ko|>
- <|fr|>
- <|ja|>
- <|pt|>
- <|tr|>
- <|pl|>
- <|ca|>
- <|nl|>
- <|ar|>
- <|sv|>
- <|it|>
- <|id|>
- <|hi|>
- <|fi|>
- <|vi|>
- <|he|>
- <|uk|>
- <|el|>
- <|ms|>
- <|cs|>
- <|ro|>
- <|da|>
- <|hu|>
- <|ta|>
- <|no|>
- <|th|>
- <|ur|>
- <|hr|>
- <|bg|>
- <|lt|>
- <|la|>
- <|mi|>
- <|ml|>
- <|cy|>
- <|sk|>
- <|te|>
- <|fa|>
- <|lv|>
- <|bn|>
- <|sr|>
- <|az|>
- <|sl|>
- <|kn|>
- <|et|>
- <|mk|>
- <|br|>
- <|eu|>
- <|is|>
- <|hy|>
- <|ne|>
- <|mn|>
- <|bs|>
- <|kk|>
- <|sq|>
- <|sw|>
- <|gl|>
- <|mr|>
- <|pa|>
- <|si|>
- <|km|>
- <|sn|>
- <|yo|>
- <|so|>
- <|af|>
- <|oc|>
- <|ka|>
- <|be|>
- <|tg|>
- <|sd|>
- <|gu|>
- <|am|>
- <|yi|>
- <|lo|>
- <|uz|>
- <|fo|>
- <|ht|>
- <|ps|>
- <|tk|>
- <|nn|>
- <|mt|>
- <|sa|>
- <|lb|>
- <|my|>
- <|bo|>
- <|tl|>
- <|mg|>
- <|as|>
- <|tt|>
- <|haw|>
- <|ln|>
- <|ha|>
- <|ba|>
- <|jw|>
- <|su|>
- <|translate|>
- <|transcribe|>
- <|startoflm|>
- <|startofprev|>
- <|nocaptions|>
- <|notimestamps|>
continuing_subword_prefix: ''
end_of_word_suffix: ''
fuse_unk: false
vocab_size: 50364
min_frequency: 2
limit_alphabet: 1000
initial_alphabet: []
show_progress: true
translate_token: <|translate|>
transcribe_token: <|transcribe|>
notimestamps_token: <|notimestamps|>
add_prefix_space: false
add_bos_token: false
model_max_length: 1024
language: persian
predict_timestamps: false