sanchit-gandhi HF staff commited on
Commit
15732ab
1 Parent(s): b712ac8
Files changed (2) hide show
  1. config.json +240 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpeechEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "hf-internal-testing/tiny-random-bart",
7
+ "activation_dropout": 0.0,
8
+ "activation_function": "gelu",
9
+ "add_cross_attention": true,
10
+ "architectures": null,
11
+ "attention_dropout": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": 0,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": 0.0,
16
+ "cross_attention_hidden_size": null,
17
+ "d_model": 16,
18
+ "decoder_attention_heads": 4,
19
+ "decoder_ffn_dim": 4,
20
+ "decoder_layerdrop": 0.0,
21
+ "decoder_layers": 2,
22
+ "decoder_start_token_id": 2,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "dropout": 0.1,
26
+ "early_stopping": false,
27
+ "encoder_attention_heads": 4,
28
+ "encoder_ffn_dim": 4,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 2,
31
+ "encoder_no_repeat_ngram_size": 0,
32
+ "eos_token_id": 2,
33
+ "exponential_decay_length_penalty": null,
34
+ "finetuning_task": null,
35
+ "forced_bos_token_id": null,
36
+ "forced_eos_token_id": 2,
37
+ "gradient_checkpointing": false,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "init_std": 0.02,
43
+ "is_decoder": true,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "length_penalty": 1.0,
50
+ "max_length": 20,
51
+ "max_position_embeddings": 100,
52
+ "min_length": 0,
53
+ "model_type": "bart",
54
+ "no_repeat_ngram_size": 0,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 2,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "scale_embedding": false,
71
+ "sep_token_id": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.21.0",
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "use_cache": true,
86
+ "vocab_size": 1000
87
+ },
88
+ "encoder": {
89
+ "_name_or_path": "hf-internal-testing/tiny-random-wav2vec2",
90
+ "activation_dropout": 0.1,
91
+ "adapter_kernel_size": 3,
92
+ "adapter_stride": 2,
93
+ "add_adapter": false,
94
+ "add_cross_attention": false,
95
+ "apply_spec_augment": true,
96
+ "architectures": null,
97
+ "attention_dropout": 0.1,
98
+ "bad_words_ids": null,
99
+ "bos_token_id": 1,
100
+ "chunk_size_feed_forward": 0,
101
+ "classifier_proj_size": 256,
102
+ "codevector_dim": 256,
103
+ "contrastive_logits_temperature": 0.1,
104
+ "conv_bias": false,
105
+ "conv_dim": [
106
+ 32,
107
+ 32,
108
+ 32
109
+ ],
110
+ "conv_kernel": [
111
+ 8,
112
+ 8,
113
+ 8
114
+ ],
115
+ "conv_stride": [
116
+ 4,
117
+ 4,
118
+ 4
119
+ ],
120
+ "cross_attention_hidden_size": null,
121
+ "ctc_loss_reduction": "sum",
122
+ "ctc_zero_infinity": false,
123
+ "decoder_start_token_id": null,
124
+ "diversity_loss_weight": 0.1,
125
+ "diversity_penalty": 0.0,
126
+ "do_sample": false,
127
+ "do_stable_layer_norm": true,
128
+ "early_stopping": false,
129
+ "encoder_no_repeat_ngram_size": 0,
130
+ "eos_token_id": 2,
131
+ "exponential_decay_length_penalty": null,
132
+ "feat_extract_activation": "gelu",
133
+ "feat_extract_dropout": 0.0,
134
+ "feat_extract_norm": "layer",
135
+ "feat_proj_dropout": 0.1,
136
+ "feat_quantizer_dropout": 0.0,
137
+ "final_dropout": 0.1,
138
+ "finetuning_task": null,
139
+ "forced_bos_token_id": null,
140
+ "forced_eos_token_id": null,
141
+ "gradient_checkpointing": false,
142
+ "hidden_act": "gelu",
143
+ "hidden_dropout": 0.1,
144
+ "hidden_dropout_prob": 0.1,
145
+ "hidden_size": 16,
146
+ "id2label": {
147
+ "0": "LABEL_0",
148
+ "1": "LABEL_1"
149
+ },
150
+ "initializer_range": 0.02,
151
+ "intermediate_size": 20,
152
+ "is_decoder": false,
153
+ "is_encoder_decoder": false,
154
+ "label2id": {
155
+ "LABEL_0": 0,
156
+ "LABEL_1": 1
157
+ },
158
+ "layer_norm_eps": 1e-05,
159
+ "layerdrop": 0.1,
160
+ "length_penalty": 1.0,
161
+ "mask_feature_length": 10,
162
+ "mask_feature_min_masks": 0,
163
+ "mask_feature_prob": 0.0,
164
+ "mask_time_length": 10,
165
+ "mask_time_min_masks": 2,
166
+ "mask_time_prob": 0.05,
167
+ "max_length": 20,
168
+ "min_length": 0,
169
+ "model_type": "wav2vec2",
170
+ "no_repeat_ngram_size": 0,
171
+ "num_adapter_layers": 3,
172
+ "num_attention_heads": 2,
173
+ "num_beam_groups": 1,
174
+ "num_beams": 1,
175
+ "num_codevector_groups": 2,
176
+ "num_codevectors_per_group": 320,
177
+ "num_conv_pos_embedding_groups": 2,
178
+ "num_conv_pos_embeddings": 16,
179
+ "num_feat_extract_layers": 3,
180
+ "num_hidden_layers": 4,
181
+ "num_negatives": 10,
182
+ "num_return_sequences": 1,
183
+ "output_attentions": false,
184
+ "output_hidden_size": 16,
185
+ "output_hidden_states": false,
186
+ "output_scores": false,
187
+ "pad_token_id": 0,
188
+ "prefix": null,
189
+ "problem_type": null,
190
+ "proj_codevector_dim": 256,
191
+ "pruned_heads": {},
192
+ "remove_invalid_values": false,
193
+ "repetition_penalty": 1.0,
194
+ "return_dict": true,
195
+ "return_dict_in_generate": false,
196
+ "sep_token_id": null,
197
+ "task_specific_params": null,
198
+ "tdnn_dilation": [
199
+ 1,
200
+ 2,
201
+ 3,
202
+ 1,
203
+ 1
204
+ ],
205
+ "tdnn_dim": [
206
+ 512,
207
+ 512,
208
+ 512,
209
+ 512,
210
+ 1500
211
+ ],
212
+ "tdnn_kernel": [
213
+ 5,
214
+ 3,
215
+ 3,
216
+ 1,
217
+ 1
218
+ ],
219
+ "temperature": 1.0,
220
+ "tf_legacy_loss": false,
221
+ "tie_encoder_decoder": false,
222
+ "tie_word_embeddings": true,
223
+ "tokenizer_class": null,
224
+ "top_k": 50,
225
+ "top_p": 1.0,
226
+ "torch_dtype": null,
227
+ "torchscript": false,
228
+ "transformers_version": "4.21.0",
229
+ "typical_p": 1.0,
230
+ "use_bfloat16": false,
231
+ "use_weighted_layer_sum": false,
232
+ "vocab_size": 32,
233
+ "xvector_output_dim": 512
234
+ },
235
+ "is_encoder_decoder": true,
236
+ "model_type": "speech-encoder-decoder",
237
+ "tie_word_embeddings": false,
238
+ "torch_dtype": "float32",
239
+ "transformers_version": null
240
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa7c60377920f2a42a2ec5752e1d800abc2b186454c70b03e41fc978d67152d5
3
+ size 241515