whisper-small.en / config.json
Xenova's picture
Xenova HF staff
Upload folder using huggingface_hub
c72244b
{
"_name_or_path": "openai/whisper-small.en",
"activation_dropout": 0.0,
"activation_function": "gelu",
"apply_spec_augment": false,
"architectures": [
"WhisperForConditionalGeneration"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": [
220,
50256
],
"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": 50257,
"dropout": 0.0,
"encoder_attention_heads": 12,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 50256,
"forced_decoder_ids": [
[
1,
50362
]
],
"init_std": 0.02,
"is_encoder_decoder": true,
"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": 448,
"max_source_positions": 1500,
"max_target_positions": 448,
"median_filter_width": 7,
"model_type": "whisper",
"num_hidden_layers": 12,
"num_mel_bins": 80,
"pad_token_id": 50256,
"scale_embedding": false,
"suppress_tokens": [
1,
2,
7,
8,
9,
10,
14,
25,
26,
27,
28,
29,
31,
58,
59,
60,
61,
62,
63,
90,
91,
92,
93,
357,
366,
438,
532,
685,
705,
796,
930,
1058,
1220,
1267,
1279,
1303,
1343,
1377,
1391,
1635,
1782,
1875,
2162,
2361,
2488,
3467,
4008,
4211,
4600,
4808,
5299,
5855,
6329,
7203,
9609,
9959,
10563,
10786,
11420,
11709,
11907,
13163,
13697,
13700,
14808,
15306,
16410,
16791,
17992,
19203,
19510,
20724,
22305,
22935,
27007,
30109,
30420,
33409,
34949,
40283,
40493,
40549,
47282,
49146,
50257,
50357,
50358,
50359,
50360,
50361
],
"transformers_version": "4.33.0.dev0",
"use_cache": true,
"use_weighted_layer_sum": false,
"vocab_size": 51864
}