Hugging Face's logo

efficient-speech
/
lite-whisper-small

Automatic Speech Recognition
Transformers
Safetensors
lite-whisper
feature-extraction
audio
whisper
hf-asr-leaderboard
custom_code
Model card Files
xet
Community
1
lite-whisper-small
File size: 2,838 Bytes 
bce99d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
144
145
 
{
  "_name_or_path": "efficient-speech/lite-whisper-small",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "apply_spec_augment": false,
  "architectures": [
    "LiteWhisperForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_lite_whisper.LiteWhisperConfig",
    "AutoModel": "modeling_lite_whisper.LiteWhisperForConditionalGeneration"
  },
  "begin_suppress_tokens": null,
  "bos_token_id": 50257,
  "classifier_proj_size": 256,
  "d_model": 768,
  "decoder_attention_heads": 12,
  "decoder_ffn_dim": 3072,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 50258,
  "dropout": 0.0,
  "encoder_attention_heads": 12,
  "encoder_ffn_dim": 3072,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 50257,
  "forced_decoder_ids": [
    [
      1,
      50259
    ],
    [
      2,
      50359
    ],
    [
      3,
      50363
    ]
  ],
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "low_rank_config": [
    {
      "fc1": 288,
      "fc2": 400,
      "k_proj": 48,
      "out_proj": 80,
      "q_proj": 48,
      "v_proj": 112
    },
    {
      "fc1": 336,
      "fc2": 608,
      "k_proj": 80,
      "out_proj": 208,
      "q_proj": 96,
      "v_proj": 208
    },
    {
      "fc1": 448,
      "k_proj": 64,
      "out_proj": 224,
      "q_proj": 96,
      "v_proj": 256
    },
    {
      "fc1": 528,
      "k_proj": 96,
      "out_proj": 288,
      "q_proj": 144,
      "v_proj": 304
    },
    {
      "fc1": 592,
      "k_proj": 208,
      "out_proj": 272,
      "q_proj": 240,
      "v_proj": 336
    },
    {
      "k_proj": 112,
      "out_proj": 288,
      "q_proj": 192,
      "v_proj": 352
    },
    {
      "fc2": 16,
      "k_proj": 192,
      "out_proj": 224,
      "q_proj": 240,
      "v_proj": 304
    },
    {
      "k_proj": 192,
      "out_proj": 320,
      "q_proj": 272,
      "v_proj": 368
    },
    {
      "k_proj": 288,
      "out_proj": 320,
      "q_proj": 304
    },
    {
      "k_proj": 288,
      "out_proj": 368,
      "q_proj": 336
    },
    {
      "k_proj": 288,
      "out_proj": 304,
      "q_proj": 336
    },
    {
      "k_proj": 256,
      "out_proj": 320,
      "q_proj": 336,
      "v_proj": 352
    }
  ],
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_time_prob": 0.05,
  "max_length": null,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "median_filter_width": 7,
  "model_type": "lite-whisper",
  "num_hidden_layers": 12,
  "num_mel_bins": 80,
  "pad_token_id": 50257,
  "scale_embedding": false,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 51865
}