Lakoc commited on
Commit
0225260
1 Parent(s): bff4994

End of training

Browse files
Files changed (5) hide show
  1. README.md +52 -0
  2. config.json +267 -0
  3. generation_config.json +15 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - common_voice_13_0
6
+ model-index:
7
+ - name: ED_small_cv_en_continue2
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # ED_small_cv_en_continue2
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the common_voice_13_0 dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0005
36
+ - train_batch_size: 256
37
+ - eval_batch_size: 64
38
+ - seed: 42
39
+ - distributed_type: multi-GPU
40
+ - num_devices: 2
41
+ - total_train_batch_size: 512
42
+ - total_eval_batch_size: 128
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 50.0
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.40.0.dev0
50
+ - Pytorch 2.2.0+rocm5.6
51
+ - Datasets 2.18.0
52
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,267 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "JointCTCAttentionEncoderDecoder"
4
+ ],
5
+ "bos_token_id": 0,
6
+ "ctc_weight": 0.3,
7
+ "decoder": {
8
+ "_name_or_path": "Lakoc/gpt2_tiny_decoder_6_layers",
9
+ "activation_function": "gelu_new",
10
+ "add_cross_attention": true,
11
+ "architectures": null,
12
+ "attn_pdrop": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 50256,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "embd_pdrop": 0.1,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 50256,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "is_decoder": true,
35
+ "is_encoder_decoder": false,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1
39
+ },
40
+ "layer_norm_epsilon": 1e-05,
41
+ "length_penalty": 1.0,
42
+ "max_length": 20,
43
+ "min_length": 0,
44
+ "model_type": "gpt2",
45
+ "n_embd": 256,
46
+ "n_head": 4,
47
+ "n_inner": 2048,
48
+ "n_layer": 6,
49
+ "n_positions": 1024,
50
+ "no_repeat_ngram_size": 0,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_size": 256,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": null,
59
+ "pos_emb_fixed": true,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "reorder_and_upcast_attn": false,
65
+ "repetition_penalty": 1.0,
66
+ "resid_pdrop": 0.1,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "scale_attn_by_inverse_layer_idx": false,
70
+ "scale_attn_weights": true,
71
+ "sep_token_id": null,
72
+ "summary_activation": null,
73
+ "summary_first_dropout": 0.1,
74
+ "summary_proj_to_labels": true,
75
+ "summary_type": "cls_index",
76
+ "summary_use_proj": true,
77
+ "suppress_tokens": null,
78
+ "task_specific_params": null,
79
+ "temperature": 1.0,
80
+ "tf_legacy_loss": false,
81
+ "tie_encoder_decoder": false,
82
+ "tie_word_embeddings": false,
83
+ "tokenizer_class": null,
84
+ "top_k": 50,
85
+ "top_p": 1.0,
86
+ "torch_dtype": null,
87
+ "torchscript": false,
88
+ "typical_p": 1.0,
89
+ "use_bfloat16": false,
90
+ "use_cache": true,
91
+ "vocab_size": 1000
92
+ },
93
+ "decoder_start_token_id": 0,
94
+ "encoder": {
95
+ "_name_or_path": "Lakoc/fisher_ebranchformer_enc_12_layers_fixed",
96
+ "activation_dropout": 0.1,
97
+ "adapter_attn_dim": null,
98
+ "adapter_kernel_size": 3,
99
+ "adapter_stride": 2,
100
+ "add_adapter": false,
101
+ "add_cross_attention": false,
102
+ "apply_spec_augment": false,
103
+ "architectures": null,
104
+ "attention_dropout": 0.1,
105
+ "bad_words_ids": null,
106
+ "begin_suppress_tokens": null,
107
+ "bos_token_id": 1,
108
+ "chunk_size_feed_forward": 0,
109
+ "classifier_proj_size": 256,
110
+ "codevector_dim": 256,
111
+ "conformer_conv_dropout": 0.1,
112
+ "contrastive_logits_temperature": 0.1,
113
+ "conv_bias": false,
114
+ "conv_depthwise_kernel_size": 31,
115
+ "conv_dim": [
116
+ 256,
117
+ 256
118
+ ],
119
+ "conv_kernel": [
120
+ 3,
121
+ 3
122
+ ],
123
+ "conv_padding": [
124
+ 1,
125
+ 1
126
+ ],
127
+ "conv_stride": [
128
+ 2,
129
+ 2
130
+ ],
131
+ "cross_attention_hidden_size": null,
132
+ "csgu_activation": "identity",
133
+ "csgu_conv_dropout": 0.1,
134
+ "csgu_kernel_size": 31,
135
+ "csgu_use_linear_after_conv": false,
136
+ "ctc_loss_reduction": "mean",
137
+ "ctc_zero_infinity": true,
138
+ "decoder_start_token_id": null,
139
+ "diversity_loss_weight": 0.1,
140
+ "diversity_penalty": 0.0,
141
+ "do_sample": false,
142
+ "do_stable_layer_norm": false,
143
+ "early_stopping": false,
144
+ "encoder_no_repeat_ngram_size": 0,
145
+ "eos_token_id": 2,
146
+ "exponential_decay_length_penalty": null,
147
+ "fe_position_embeddings": false,
148
+ "feat_extract_activation": "gelu",
149
+ "feat_extract_norm": "group",
150
+ "feat_proj_dropout": 0.0,
151
+ "feat_quantizer_dropout": 0.0,
152
+ "final_dropout": 0.1,
153
+ "finetuning_task": null,
154
+ "forced_bos_token_id": null,
155
+ "forced_eos_token_id": null,
156
+ "hidden_act": "gelu",
157
+ "hidden_dropout": 0.1,
158
+ "hidden_size": 256,
159
+ "id2label": {
160
+ "0": "LABEL_0",
161
+ "1": "LABEL_1"
162
+ },
163
+ "initializer_range": 0.02,
164
+ "intermediate_size": 1024,
165
+ "is_causal": false,
166
+ "is_decoder": false,
167
+ "is_encoder_decoder": false,
168
+ "label2id": {
169
+ "LABEL_0": 0,
170
+ "LABEL_1": 1
171
+ },
172
+ "layer_norm_eps": 1e-05,
173
+ "layerdrop": 0.0,
174
+ "length_penalty": 1.0,
175
+ "mask_feature_length": 10,
176
+ "mask_feature_min_masks": 0,
177
+ "mask_feature_prob": 0.0,
178
+ "mask_time_length": 10,
179
+ "mask_time_min_masks": 2,
180
+ "mask_time_prob": 0.05,
181
+ "max_length": 20,
182
+ "max_source_positions": 1024,
183
+ "merge_conv_kernel": 31,
184
+ "min_length": 0,
185
+ "model_type": "wav2vec2-ebranchformer",
186
+ "no_repeat_ngram_size": 0,
187
+ "num_adapter_layers": 3,
188
+ "num_attention_heads": 4,
189
+ "num_beam_groups": 1,
190
+ "num_beams": 1,
191
+ "num_codevector_groups": 2,
192
+ "num_codevectors_per_group": 320,
193
+ "num_conv_pos_embedding_groups": 16,
194
+ "num_conv_pos_embeddings": 128,
195
+ "num_fbanks": 80,
196
+ "num_feat_extract_layers": 2,
197
+ "num_hidden_layers": 12,
198
+ "num_mel_bins": 80,
199
+ "num_negatives": 100,
200
+ "num_return_sequences": 1,
201
+ "output_attentions": false,
202
+ "output_hidden_size": 256,
203
+ "output_hidden_states": false,
204
+ "output_scores": false,
205
+ "pad_token_id": 3,
206
+ "position_embeddings_type": "relative",
207
+ "prefix": null,
208
+ "problem_type": null,
209
+ "proj_codevector_dim": 256,
210
+ "pruned_heads": {},
211
+ "remove_invalid_values": false,
212
+ "repetition_penalty": 1.0,
213
+ "return_dict": true,
214
+ "return_dict_in_generate": false,
215
+ "rotary_embedding_base": 10000,
216
+ "sep_token_id": null,
217
+ "suppress_tokens": null,
218
+ "task_specific_params": null,
219
+ "tdnn_dilation": [
220
+ 1,
221
+ 2,
222
+ 3,
223
+ 1,
224
+ 1
225
+ ],
226
+ "tdnn_dim": [
227
+ 512,
228
+ 512,
229
+ 512,
230
+ 512,
231
+ 1500
232
+ ],
233
+ "tdnn_kernel": [
234
+ 5,
235
+ 3,
236
+ 3,
237
+ 1,
238
+ 1
239
+ ],
240
+ "temperature": 1.0,
241
+ "tf_legacy_loss": false,
242
+ "tie_encoder_decoder": false,
243
+ "tie_word_embeddings": true,
244
+ "tokenizer_class": null,
245
+ "top_k": 50,
246
+ "top_p": 1.0,
247
+ "torch_dtype": null,
248
+ "torchscript": false,
249
+ "typical_p": 1.0,
250
+ "use_bfloat16": false,
251
+ "use_fbanks": true,
252
+ "use_macaron_ff": true,
253
+ "use_weighted_layer_sum": false,
254
+ "vocab_size": 1000,
255
+ "xvector_output_dim": 512
256
+ },
257
+ "eos_token_id": 1,
258
+ "is_encoder_decoder": true,
259
+ "lsm_factor": 0.1,
260
+ "mask_token_id": 4,
261
+ "model_type": "joint_aed_ctc_speech-encoder-decoder",
262
+ "pad_token_id": 3,
263
+ "shared_lm_head": false,
264
+ "tie_word_embeddings": false,
265
+ "torch_dtype": "float32",
266
+ "transformers_version": "4.40.0.dev0"
267
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_eos_space_trick": false,
3
+ "bos_token_id": 0,
4
+ "ctc_margin": 0,
5
+ "ctc_weight": 0.3,
6
+ "decoder_start_token_id": 0,
7
+ "eos_space_trick_weight": 0.0,
8
+ "eos_token_id": 1,
9
+ "lm_model": null,
10
+ "lm_weight": 0.0,
11
+ "max_length": 512,
12
+ "pad_token_id": 3,
13
+ "space_token_id": -1,
14
+ "transformers_version": "4.40.0.dev0"
15
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ad2d85848146f6600290cb3d0e5de191445903a4cd7506d377c82a4b1fccdc
3
+ size 143219080
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db5562fb05c74b4caf880edd897b20d37a53978dcaf90e391a126ce3933b593d
3
+ size 5816