Hugging Face's logo

elsayedissa
/
wav2vec2-xls-r-300m-ar

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
arabic_speech_corpus
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
elsayedissa commited on
Commit
22fd223
•
1 Parent(s): ca0b026

Training in progress, step 1000

Browse files
Files changed (15) hide show
  1. .gitignore +1 -0
  2. config.json +107 -0
  3. last-checkpoint/config.json +107 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/preprocessor_config.json +9 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/trainer_state.json +265 -0
  10. last-checkpoint/training_args.bin +3 -0
  11. preprocessor_config.json +9 -0
  12. pytorch_model.bin +3 -0
  13. runs/Apr09_14-45-21_gpu07.cyverse.org/1681076808.4547613/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.1 +3 -0
  14. runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0 +3 -0
  15. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.05,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_codevector_groups": 2,
72
+ "num_codevectors_per_group": 320,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 77,
80
+ "proj_codevector_dim": 768,
81
+ "tdnn_dilation": [
82
+ 1,
83
+ 2,
84
+ 3,
85
+ 1,
86
+ 1
87
+ ],
88
+ "tdnn_dim": [
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 1500
94
+ ],
95
+ "tdnn_kernel": [
96
+ 5,
97
+ 3,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.28.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 80,
106
+ "xvector_output_dim": 512
107
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.05,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_codevector_groups": 2,
72
+ "num_codevectors_per_group": 320,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 77,
80
+ "proj_codevector_dim": 768,
81
+ "tdnn_dilation": [
82
+ 1,
83
+ 2,
84
+ 3,
85
+ 1,
86
+ 1
87
+ ],
88
+ "tdnn_dim": [
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 1500
94
+ ],
95
+ "tdnn_kernel": [
96
+ 5,
97
+ 3,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.28.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 80,
106
+ "xvector_output_dim": 512
107
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbbaa276202fa979205f050d64ec0fb23b7d02bcc83d371bf853f236d4705b1
3
+ size 2524414853
last-checkpoint/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a804cb4638c6b5cb2ed7579b53ad7958115a6c4f0fb821c0582d87f7b54620e
3
+ size 1262229869
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35bd2fb5b221148ef9f3df4d84de356b110717172d9465cad80304a59c6933a
3
+ size 14639
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf9887d830501ed44fcfc9b1240b3894b0a39f156a92a6534273c610fd7f49b
3
+ size 627
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.07856032524213799,
3
+ "best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-1000",
4
+ "epoch": 8.849557522123893,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.22,
12
+ "learning_rate": 1.4999999999999999e-05,
13
+ "loss": 9.1248,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.44,
18
+ "learning_rate": 2.9999999999999997e-05,
19
+ "loss": 6.6739,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.66,
24
+ "learning_rate": 4.4999999999999996e-05,
25
+ "loss": 4.632,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.88,
30
+ "learning_rate": 5.9999999999999995e-05,
31
+ "loss": 3.917,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 1.11,
36
+ "learning_rate": 7.5e-05,
37
+ "loss": 3.3449,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 1.33,
42
+ "learning_rate": 8.999999999999999e-05,
43
+ "loss": 2.8486,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 1.55,
48
+ "learning_rate": 0.00010499999999999999,
49
+ "loss": 2.5717,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 1.77,
54
+ "learning_rate": 0.00011999999999999999,
55
+ "loss": 2.3746,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 1.99,
60
+ "learning_rate": 0.000135,
61
+ "loss": 2.2744,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 2.21,
66
+ "learning_rate": 0.00015,
67
+ "loss": 2.0759,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 2.43,
72
+ "learning_rate": 0.000165,
73
+ "loss": 1.7813,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 2.65,
78
+ "learning_rate": 0.00017999999999999998,
79
+ "loss": 1.2002,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 2.88,
84
+ "learning_rate": 0.000195,
85
+ "loss": 0.7684,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 3.1,
90
+ "learning_rate": 0.00020999999999999998,
91
+ "loss": 0.527,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 3.32,
96
+ "learning_rate": 0.000225,
97
+ "loss": 0.3734,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 3.54,
102
+ "learning_rate": 0.00023999999999999998,
103
+ "loss": 0.3184,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 3.76,
108
+ "learning_rate": 0.00025499999999999996,
109
+ "loss": 0.2822,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 3.98,
114
+ "learning_rate": 0.00027,
115
+ "loss": 0.2074,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 4.2,
120
+ "learning_rate": 0.000285,
121
+ "loss": 0.1985,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 4.42,
126
+ "learning_rate": 0.0003,
127
+ "loss": 0.1917,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 4.65,
132
+ "learning_rate": 0.00029921052631578946,
133
+ "loss": 0.1853,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 4.87,
138
+ "learning_rate": 0.00029842105263157894,
139
+ "loss": 0.1828,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 5.09,
144
+ "learning_rate": 0.00029763157894736837,
145
+ "loss": 0.1715,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 5.31,
150
+ "learning_rate": 0.00029684210526315785,
151
+ "loss": 0.1457,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 5.53,
156
+ "learning_rate": 0.00029605263157894733,
157
+ "loss": 0.1247,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 5.75,
162
+ "learning_rate": 0.0002952631578947368,
163
+ "loss": 0.1266,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 5.97,
168
+ "learning_rate": 0.0002944736842105263,
169
+ "loss": 0.117,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 6.19,
174
+ "learning_rate": 0.0002936842105263158,
175
+ "loss": 0.117,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 6.42,
180
+ "learning_rate": 0.00029289473684210527,
181
+ "loss": 0.125,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 6.64,
186
+ "learning_rate": 0.0002921052631578947,
187
+ "loss": 0.1084,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 6.86,
192
+ "learning_rate": 0.0002913157894736842,
193
+ "loss": 0.1178,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 7.08,
198
+ "learning_rate": 0.00029052631578947366,
199
+ "loss": 0.1193,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 7.3,
204
+ "learning_rate": 0.00028973684210526314,
205
+ "loss": 0.0925,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 7.52,
210
+ "learning_rate": 0.00028894736842105263,
211
+ "loss": 0.085,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 7.74,
216
+ "learning_rate": 0.00028815789473684206,
217
+ "loss": 0.0865,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 7.96,
222
+ "learning_rate": 0.00028736842105263154,
223
+ "loss": 0.0811,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 8.19,
228
+ "learning_rate": 0.000286578947368421,
229
+ "loss": 0.0835,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 8.41,
234
+ "learning_rate": 0.0002857894736842105,
235
+ "loss": 0.0886,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 8.63,
240
+ "learning_rate": 0.000285,
241
+ "loss": 0.0991,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 8.85,
246
+ "learning_rate": 0.0002842105263157894,
247
+ "loss": 0.0793,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 8.85,
252
+ "eval_loss": 0.16262491047382355,
253
+ "eval_runtime": 11.6481,
254
+ "eval_samples_per_second": 8.585,
255
+ "eval_steps_per_second": 1.116,
256
+ "eval_wer": 0.07856032524213799,
257
+ "step": 1000
258
+ }
259
+ ],
260
+ "max_steps": 10000,
261
+ "num_train_epochs": 89,
262
+ "total_flos": 3.9707238818974925e+18,
263
+ "trial_name": null,
264
+ "trial_params": null
265
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140f36b5c5e5d4e41aec29f201896ff2d99717b8f4cd11abdc87a591034d71fd
3
+ size 3643
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a804cb4638c6b5cb2ed7579b53ad7958115a6c4f0fb821c0582d87f7b54620e
3
+ size 1262229869
runs/Apr09_14-45-21_gpu07.cyverse.org/1681076808.4547613/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7bd378d72ebe7130c076a45b31263ba91ac4cc50b961bc4c61bfe4aa2ba7437
3
+ size 5854
runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540382d84d95bb9fbcb54bd2eae7512adb538af0c7b45e172684e621105bd32b
3
+ size 11980
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140f36b5c5e5d4e41aec29f201896ff2d99717b8f4cd11abdc87a591034d71fd
3
+ size 3643