Hugging Face's logo

BUT-FIT
/
DiCoW_v3_2

Automatic Speech Recognition
Transformers
Safetensors
DiCoW
speech
whisper
multilingual
speaker-diarization
meeting-transcription
BUT-FIT
custom_code
Model card Files
xet
 Community
2
DiCoW_v3_2
File size: 2,186 Bytes
445d92b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "additional_special_tokens": [
    "<|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|>",
    "<|yue|>",
    "<|translate|>",
    "<|transcribe|>",
    "<|startoflm|>",
    "<|startofprev|>",
    "<|nospeech|>",
    "<|notimestamps|>"
  ],
  "bos_token": {
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "pad_token": {
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "unk_token": {
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  }
}