giangndm commited on
Commit
4a0b888
·
verified ·
1 Parent(s): ad627c3

Upload whisper encoder

Browse files
Files changed (2) hide show
  1. config.json +201 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 51865,
3
+ "num_mel_bins": 80,
4
+ "d_model": 768,
5
+ "encoder_layers": 12,
6
+ "encoder_attention_heads": 12,
7
+ "decoder_layers": 12,
8
+ "decoder_attention_heads": 12,
9
+ "decoder_ffn_dim": 3072,
10
+ "encoder_ffn_dim": 3072,
11
+ "dropout": 0.0,
12
+ "attention_dropout": 0.0,
13
+ "activation_dropout": 0.0,
14
+ "activation_function": "gelu",
15
+ "init_std": 0.02,
16
+ "encoder_layerdrop": 0.0,
17
+ "decoder_layerdrop": 0.0,
18
+ "use_cache": true,
19
+ "num_hidden_layers": 12,
20
+ "scale_embedding": false,
21
+ "max_source_positions": 1500,
22
+ "max_target_positions": 448,
23
+ "classifier_proj_size": 256,
24
+ "use_weighted_layer_sum": false,
25
+ "apply_spec_augment": false,
26
+ "mask_time_prob": 0.05,
27
+ "mask_time_length": 10,
28
+ "mask_time_min_masks": 2,
29
+ "mask_feature_prob": 0.0,
30
+ "mask_feature_length": 10,
31
+ "mask_feature_min_masks": 0,
32
+ "median_filter_width": 7,
33
+ "return_dict": true,
34
+ "output_hidden_states": false,
35
+ "torchscript": false,
36
+ "torch_dtype": "bfloat16",
37
+ "use_bfloat16": false,
38
+ "tf_legacy_loss": false,
39
+ "pruned_heads": {},
40
+ "tie_word_embeddings": true,
41
+ "chunk_size_feed_forward": 0,
42
+ "is_encoder_decoder": true,
43
+ "is_decoder": false,
44
+ "cross_attention_hidden_size": null,
45
+ "add_cross_attention": false,
46
+ "tie_encoder_decoder": false,
47
+ "max_length": 448,
48
+ "min_length": 0,
49
+ "do_sample": false,
50
+ "early_stopping": false,
51
+ "num_beams": 1,
52
+ "num_beam_groups": 1,
53
+ "diversity_penalty": 0.0,
54
+ "temperature": 1.0,
55
+ "top_k": 50,
56
+ "top_p": 1.0,
57
+ "typical_p": 1.0,
58
+ "repetition_penalty": 1.0,
59
+ "length_penalty": 1.0,
60
+ "no_repeat_ngram_size": 0,
61
+ "encoder_no_repeat_ngram_size": 0,
62
+ "bad_words_ids": null,
63
+ "num_return_sequences": 1,
64
+ "output_scores": false,
65
+ "return_dict_in_generate": false,
66
+ "forced_bos_token_id": null,
67
+ "forced_eos_token_id": null,
68
+ "remove_invalid_values": false,
69
+ "exponential_decay_length_penalty": null,
70
+ "suppress_tokens": [
71
+ 1,
72
+ 2,
73
+ 7,
74
+ 8,
75
+ 9,
76
+ 10,
77
+ 14,
78
+ 25,
79
+ 26,
80
+ 27,
81
+ 28,
82
+ 29,
83
+ 31,
84
+ 58,
85
+ 59,
86
+ 60,
87
+ 61,
88
+ 62,
89
+ 63,
90
+ 90,
91
+ 91,
92
+ 92,
93
+ 93,
94
+ 359,
95
+ 503,
96
+ 522,
97
+ 542,
98
+ 873,
99
+ 893,
100
+ 902,
101
+ 918,
102
+ 922,
103
+ 931,
104
+ 1350,
105
+ 1853,
106
+ 1982,
107
+ 2460,
108
+ 2627,
109
+ 3246,
110
+ 3253,
111
+ 3268,
112
+ 3536,
113
+ 3846,
114
+ 3961,
115
+ 4183,
116
+ 4667,
117
+ 6585,
118
+ 6647,
119
+ 7273,
120
+ 9061,
121
+ 9383,
122
+ 10428,
123
+ 10929,
124
+ 11938,
125
+ 12033,
126
+ 12331,
127
+ 12562,
128
+ 13793,
129
+ 14157,
130
+ 14635,
131
+ 15265,
132
+ 15618,
133
+ 16553,
134
+ 16604,
135
+ 18362,
136
+ 18956,
137
+ 20075,
138
+ 21675,
139
+ 22520,
140
+ 26130,
141
+ 26161,
142
+ 26435,
143
+ 28279,
144
+ 29464,
145
+ 31650,
146
+ 32302,
147
+ 32470,
148
+ 36865,
149
+ 42863,
150
+ 47425,
151
+ 49870,
152
+ 50254,
153
+ 50258,
154
+ 50360,
155
+ 50361,
156
+ 50362
157
+ ],
158
+ "begin_suppress_tokens": [
159
+ 220,
160
+ 50257
161
+ ],
162
+ "architectures": [
163
+ "WhisperForConditionalGeneration"
164
+ ],
165
+ "finetuning_task": null,
166
+ "id2label": {
167
+ "0": "LABEL_0",
168
+ "1": "LABEL_1"
169
+ },
170
+ "label2id": {
171
+ "LABEL_0": 0,
172
+ "LABEL_1": 1
173
+ },
174
+ "tokenizer_class": null,
175
+ "prefix": null,
176
+ "bos_token_id": 50257,
177
+ "pad_token_id": 50257,
178
+ "eos_token_id": 50257,
179
+ "sep_token_id": null,
180
+ "decoder_start_token_id": 50258,
181
+ "task_specific_params": null,
182
+ "problem_type": null,
183
+ "_name_or_path": "openai/whisper-small",
184
+ "transformers_version": "4.53.1",
185
+ "forced_decoder_ids": [
186
+ [
187
+ 1,
188
+ 50259
189
+ ],
190
+ [
191
+ 2,
192
+ 50359
193
+ ],
194
+ [
195
+ 3,
196
+ 50363
197
+ ]
198
+ ],
199
+ "model_type": "whisper",
200
+ "output_attentions": false
201
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e3fd8829989aae1566813d94756b8897a55e6b2dac62db9d2782945cf6dd25
3
+ size 176326856