Hugging Face's logo

waveletdeboshir
/
whisper-base-ru-pruned-ft

Automatic Speech Recognition
Transformers
Safetensors
Russian
whisper
asr
Pytorch
pruned
finetune
audio
Eval Results
Inference Endpoints
Model card Files Community
whisper-base-ru-pruned-ft
File size: 2,965 Bytes 
c319bed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "add_bos_token": false,
    "add_prefix_space": false,
    "added_tokens_decoder": {
        "4197": {
            "content": "<|endoftext|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4198": {
            "content": "<|startoftranscript|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4199": {
            "content": "<|en|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4200": {
            "content": "<|ru|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4201": {
            "content": "<|translate|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4202": {
            "content": "<|transcribe|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4203": {
            "content": "<|startoflm|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4204": {
            "content": "<|startofprev|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4205": {
            "content": "<|nocaptions|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4206": {
            "content": "<|notimestamps|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        }
    },
    "additional_special_tokens": [
        "<|endoftext|>",
        "<|startoftranscript|>",
        "<|en|>",
        "<|ru|>",
        "<|translate|>",
        "<|transcribe|>",
        "<|startoflm|>",
        "<|startofprev|>",
        "<|nocaptions|>",
        "<|notimestamps|>"
    ],
    "bos_token": "<|endoftext|>",
    "clean_up_tokenization_spaces": true,
    "eos_token": "<|endoftext|>",
    "errors": "replace",
    "model_max_length": 1024,
    "pad_token": "<|endoftext|>",
    "processor_class": "WhisperProcessor",
    "return_attention_mask": false,
    "tokenizer_class": "WhisperTokenizer",
    "unk_token": "<|endoftext|>"
}