Hugging Face's logo

bkh6722
/
bach-arb

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Model card Files
xet
 Metrics Community
bkh6722 commited on
Commit
ef43d90
·
1 Parent(s): 4ec3e28

add tokenizer

Browse files
Files changed (11) hide show
  1. runs/wav2vec-vlbg-MW/1652204555.1675315/events.out.tfevents.1652204555.726f2b3fea59.25433.1 +0 -3
  2. runs/wav2vec-vlbg-MW/events.out.tfevents.1652204555.726f2b3fea59.25433.0 +0 -3
  3. wav2vec-vlbg-MW/config.json +0 -80
  4. wav2vec-vlbg-MW/optimizer.pt +0 -3
  5. wav2vec-vlbg-MW/preprocessor_config.json +0 -9
  6. wav2vec-vlbg-MW/pytorch_model.bin +0 -3
  7. wav2vec-vlbg-MW/rng_state.pth +0 -3
  8. wav2vec-vlbg-MW/scaler.pt +0 -3
  9. wav2vec-vlbg-MW/scheduler.pt +0 -3
  10. wav2vec-vlbg-MW/trainer_state.json +0 -211
  11. wav2vec-vlbg-MW/training_args.bin +0 -3
runs/wav2vec-vlbg-MW/1652204555.1675315/events.out.tfevents.1652204555.726f2b3fea59.25433.1 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c7e854a8b305c068ccc5eefb8b19cc4901a5fe0f5418564ceda49cbca8d4047
3
- size 4489
 
 
 
 
runs/wav2vec-vlbg-MW/events.out.tfevents.1652204555.726f2b3fea59.25433.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:71db4784ded84d8076c817f26639cb241cfea5c7f923354d454eb49b0ea5c978
3
- size 13632
 
 
 
 
wav2vec-vlbg-MW/config.json DELETED
@@ -1,80 +0,0 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-base-960h",
3
- "activation_dropout": 0.1,
4
- "apply_spec_augment": true,
5
- "architectures": [
6
- "Wav2Vec2ForCTC"
7
- ],
8
- "attention_dropout": 0.5,
9
- "bos_token_id": 1,
10
- "classifier_proj_size": 256,
11
- "codevector_dim": 256,
12
- "contrastive_logits_temperature": 0.1,
13
- "conv_bias": false,
14
- "conv_dim": [
15
- 512,
16
- 512,
17
- 512,
18
- 512,
19
- 512,
20
- 512,
21
- 512
22
- ],
23
- "conv_kernel": [
24
- 10,
25
- 3,
26
- 3,
27
- 3,
28
- 3,
29
- 2,
30
- 2
31
- ],
32
- "conv_stride": [
33
- 5,
34
- 2,
35
- 2,
36
- 2,
37
- 2,
38
- 2,
39
- 2
40
- ],
41
- "ctc_loss_reduction": "mean",
42
- "ctc_zero_infinity": false,
43
- "diversity_loss_weight": 0.1,
44
- "do_stable_layer_norm": false,
45
- "eos_token_id": 2,
46
- "feat_extract_activation": "gelu",
47
- "feat_extract_dropout": 0.0,
48
- "feat_extract_norm": "group",
49
- "feat_proj_dropout": 0.0,
50
- "feat_quantizer_dropout": 0.0,
51
- "final_dropout": 0.1,
52
- "gradient_checkpointing": false,
53
- "hidden_act": "gelu",
54
- "hidden_dropout": 0.0,
55
- "hidden_dropout_prob": 0.1,
56
- "hidden_size": 768,
57
- "initializer_range": 0.02,
58
- "intermediate_size": 3072,
59
- "layer_norm_eps": 1e-05,
60
- "layerdrop": 0.0,
61
- "mask_feature_length": 10,
62
- "mask_feature_prob": 0.0,
63
- "mask_time_length": 10,
64
- "mask_time_prob": 0.05,
65
- "model_type": "wav2vec2",
66
- "num_attention_heads": 12,
67
- "num_codevector_groups": 2,
68
- "num_codevectors_per_group": 320,
69
- "num_conv_pos_embedding_groups": 16,
70
- "num_conv_pos_embeddings": 128,
71
- "num_feat_extract_layers": 7,
72
- "num_hidden_layers": 12,
73
- "num_negatives": 100,
74
- "pad_token_id": 26,
75
- "proj_codevector_dim": 256,
76
- "torch_dtype": "float32",
77
- "transformers_version": "4.11.3",
78
- "use_weighted_layer_sum": false,
79
- "vocab_size": 32
80
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
wav2vec-vlbg-MW/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:79a2811a89711295998bfb2c18a244ba1bf1c3bc6e8985402a1a1b81249fa75e
3
- size 721685265
 
 
 
 
wav2vec-vlbg-MW/preprocessor_config.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "do_normalize": true,
3
- "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
- "feature_size": 1,
5
- "padding_side": "right",
6
- "padding_value": 0.0,
7
- "return_attention_mask": true,
8
- "sampling_rate": 16000
9
- }
 
 
 
 
 
 
 
 
 
 
wav2vec-vlbg-MW/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8909defc3cfc80e6b475ceee85e815fd923c580f1511cb1643393e515feb106
3
- size 377670039
 
 
 
 
wav2vec-vlbg-MW/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:389b39bc8670d836abf3b9aac21c1ee40b37ddc4c841788548f2236180c29608
3
- size 14567
 
 
 
 
wav2vec-vlbg-MW/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c33a536167719b6e259a041f22f1cf5636960275aa70b4ce1df2e294934bde6
3
- size 559
 
 
 
 
wav2vec-vlbg-MW/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7f75d9feebadf0d4f1149bfaf72f291ca0d2c3ddba54fa618274654c1a6ab9c
3
- size 623
 
 
 
 
wav2vec-vlbg-MW/trainer_state.json DELETED
@@ -1,211 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 260.0,
5
- "global_step": 1300,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 20.0,
12
- "learning_rate": 5.76e-05,
13
- "loss": 5.5776,
14
- "step": 100
15
- },
16
- {
17
- "epoch": 20.0,
18
- "eval_loss": 36.25331497192383,
19
- "eval_runtime": 0.6005,
20
- "eval_samples_per_second": 43.298,
21
- "eval_steps_per_second": 6.661,
22
- "eval_wer": 1.0,
23
- "step": 100
24
- },
25
- {
26
- "epoch": 40.0,
27
- "learning_rate": 0.0001176,
28
- "loss": 2.9662,
29
- "step": 200
30
- },
31
- {
32
- "epoch": 40.0,
33
- "eval_loss": 19.664457321166992,
34
- "eval_runtime": 0.5933,
35
- "eval_samples_per_second": 43.819,
36
- "eval_steps_per_second": 6.741,
37
- "eval_wer": 1.0,
38
- "step": 200
39
- },
40
- {
41
- "epoch": 60.0,
42
- "learning_rate": 0.00017759999999999998,
43
- "loss": 2.8096,
44
- "step": 300
45
- },
46
- {
47
- "epoch": 60.0,
48
- "eval_loss": 41.18692398071289,
49
- "eval_runtime": 0.6025,
50
- "eval_samples_per_second": 43.153,
51
- "eval_steps_per_second": 6.639,
52
- "eval_wer": 1.162162162162162,
53
- "step": 300
54
- },
55
- {
56
- "epoch": 80.0,
57
- "learning_rate": 0.0002376,
58
- "loss": 2.4675,
59
- "step": 400
60
- },
61
- {
62
- "epoch": 80.0,
63
- "eval_loss": 27.60628890991211,
64
- "eval_runtime": 0.6028,
65
- "eval_samples_per_second": 43.135,
66
- "eval_steps_per_second": 6.636,
67
- "eval_wer": 1.5135135135135136,
68
- "step": 400
69
- },
70
- {
71
- "epoch": 100.0,
72
- "learning_rate": 0.00029759999999999997,
73
- "loss": 1.7554,
74
- "step": 500
75
- },
76
- {
77
- "epoch": 100.0,
78
- "eval_loss": 40.952999114990234,
79
- "eval_runtime": 0.5943,
80
- "eval_samples_per_second": 43.749,
81
- "eval_steps_per_second": 6.731,
82
- "eval_wer": 1.7027027027027026,
83
- "step": 500
84
- },
85
- {
86
- "epoch": 120.0,
87
- "learning_rate": 0.0002869090909090909,
88
- "loss": 1.0254,
89
- "step": 600
90
- },
91
- {
92
- "epoch": 120.0,
93
- "eval_loss": 32.34526824951172,
94
- "eval_runtime": 0.5931,
95
- "eval_samples_per_second": 43.834,
96
- "eval_steps_per_second": 6.744,
97
- "eval_wer": 1.8108108108108107,
98
- "step": 600
99
- },
100
- {
101
- "epoch": 140.0,
102
- "learning_rate": 0.00027327272727272725,
103
- "loss": 0.6174,
104
- "step": 700
105
- },
106
- {
107
- "epoch": 140.0,
108
- "eval_loss": 34.84318923950195,
109
- "eval_runtime": 0.5959,
110
- "eval_samples_per_second": 43.629,
111
- "eval_steps_per_second": 6.712,
112
- "eval_wer": 1.864864864864865,
113
- "step": 700
114
- },
115
- {
116
- "epoch": 160.0,
117
- "learning_rate": 0.00025963636363636363,
118
- "loss": 0.4281,
119
- "step": 800
120
- },
121
- {
122
- "epoch": 160.0,
123
- "eval_loss": 36.15171813964844,
124
- "eval_runtime": 0.5965,
125
- "eval_samples_per_second": 43.588,
126
- "eval_steps_per_second": 6.706,
127
- "eval_wer": 1.864864864864865,
128
- "step": 800
129
- },
130
- {
131
- "epoch": 180.0,
132
- "learning_rate": 0.00024613636363636363,
133
- "loss": 0.324,
134
- "step": 900
135
- },
136
- {
137
- "epoch": 180.0,
138
- "eval_loss": 37.320735931396484,
139
- "eval_runtime": 0.5968,
140
- "eval_samples_per_second": 43.567,
141
- "eval_steps_per_second": 6.703,
142
- "eval_wer": 1.8918918918918919,
143
- "step": 900
144
- },
145
- {
146
- "epoch": 200.0,
147
- "learning_rate": 0.00023249999999999999,
148
- "loss": 0.2476,
149
- "step": 1000
150
- },
151
- {
152
- "epoch": 200.0,
153
- "eval_loss": 41.81070327758789,
154
- "eval_runtime": 0.5943,
155
- "eval_samples_per_second": 43.747,
156
- "eval_steps_per_second": 6.73,
157
- "eval_wer": 1.864864864864865,
158
- "step": 1000
159
- },
160
- {
161
- "epoch": 220.0,
162
- "learning_rate": 0.00021899999999999998,
163
- "loss": 0.2166,
164
- "step": 1100
165
- },
166
- {
167
- "epoch": 220.0,
168
- "eval_loss": 39.16055679321289,
169
- "eval_runtime": 0.5903,
170
- "eval_samples_per_second": 44.046,
171
- "eval_steps_per_second": 6.776,
172
- "eval_wer": 1.8918918918918919,
173
- "step": 1100
174
- },
175
- {
176
- "epoch": 240.0,
177
- "learning_rate": 0.00020536363636363637,
178
- "loss": 0.1803,
179
- "step": 1200
180
- },
181
- {
182
- "epoch": 240.0,
183
- "eval_loss": 41.908931732177734,
184
- "eval_runtime": 0.5698,
185
- "eval_samples_per_second": 45.631,
186
- "eval_steps_per_second": 7.02,
187
- "eval_wer": 1.8918918918918919,
188
- "step": 1200
189
- },
190
- {
191
- "epoch": 260.0,
192
- "learning_rate": 0.0001917272727272727,
193
- "loss": 0.1429,
194
- "step": 1300
195
- },
196
- {
197
- "epoch": 260.0,
198
- "eval_loss": 39.956539154052734,
199
- "eval_runtime": 0.592,
200
- "eval_samples_per_second": 43.917,
201
- "eval_steps_per_second": 6.756,
202
- "eval_wer": 1.837837837837838,
203
- "step": 1300
204
- }
205
- ],
206
- "max_steps": 2700,
207
- "num_train_epochs": 540,
208
- "total_flos": 1.6132333708441843e+18,
209
- "trial_name": null,
210
- "trial_params": null
211
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
wav2vec-vlbg-MW/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:682fecbdd7eb89fec95b3ed1a209e233fa42412664c99cdc38e76cd95320a6d3
3
- size 2799