Hugging Face's logo

marinone94
/
xls-r-300m-sv-robust

Automatic Speech Recognition
Transformers
PyTorch
Swedish
wav2vec2
mozilla-foundation/common_voice_9_0
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
marinone94 commited on
Commit
de66726
•
1 Parent(s): adb7bc0

Training in progress, step 300

Browse files
Files changed (10) hide show
  1. checkpoint-300/config.json +115 -0
  2. checkpoint-300/optimizer.pt +3 -0
  3. checkpoint-300/preprocessor_config.json +9 -0
  4. checkpoint-300/pytorch_model.bin +3 -0
  5. checkpoint-300/rng_state.pth +3 -0
  6. checkpoint-300/scaler.pt +3 -0
  7. checkpoint-300/scheduler.pt +3 -0
  8. checkpoint-300/trainer_state.json +223 -0
  9. checkpoint-300/training_args.bin +3 -0
  10. pytorch_model.bin +1 -1
checkpoint-300/config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "KBLab/wav2vec2-large-voxrex",
3
+ "activation_dropout": 0.1,
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_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 64,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.25,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.75,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "num_adapter_layers": 3,
78
+ "num_attention_heads": 16,
79
+ "num_codevector_groups": 2,
80
+ "num_codevectors_per_group": 320,
81
+ "num_conv_pos_embedding_groups": 16,
82
+ "num_conv_pos_embeddings": 128,
83
+ "num_feat_extract_layers": 7,
84
+ "num_hidden_layers": 24,
85
+ "num_negatives": 100,
86
+ "output_hidden_size": 1024,
87
+ "pad_token_id": 32,
88
+ "proj_codevector_dim": 768,
89
+ "tdnn_dilation": [
90
+ 1,
91
+ 2,
92
+ 3,
93
+ 1,
94
+ 1
95
+ ],
96
+ "tdnn_dim": [
97
+ 512,
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 1500
102
+ ],
103
+ "tdnn_kernel": [
104
+ 5,
105
+ 3,
106
+ 3,
107
+ 1,
108
+ 1
109
+ ],
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.17.0.dev0",
112
+ "use_weighted_layer_sum": false,
113
+ "vocab_size": 35,
114
+ "xvector_output_dim": 512
115
+ }
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b233d43f29a6e036b79c44651fd2c0fc0d4070bbff113ccf5079df119e688312
3
+ size 2490346001
checkpoint-300/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
+ }
checkpoint-300/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68645628512b23e8cf87be35a11a95bbf653c484127f9db2e43ac576589c37b8
3
+ size 1262067185
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa37c470d6b5b3178606237196b01db492c1933d0eac1b5cac41030d832a2c9
3
+ size 14567
checkpoint-300/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1e02160a95d49a675cbb9a046de5c535a710ba6e764888e1228126b79ea4baa
3
+ size 559
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1beff8a4e86c642259673b144c29b5166149cdf4fb75d2a4f6655ed65a03fb
3
+ size 623
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.1384083044982699,
5
+ "global_step": 300,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 5.725190839694656e-06,
13
+ "loss": 12.7187,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 1.1450381679389312e-05,
19
+ "loss": 13.2124,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 1.6603053435114505e-05,
25
+ "loss": 14.1489,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 2.1755725190839692e-05,
31
+ "loss": 25.9008,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.02,
36
+ "learning_rate": 2.6908396946564882e-05,
37
+ "loss": 31.3861,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 3.263358778625954e-05,
43
+ "loss": 8.9557,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "learning_rate": 3.835877862595419e-05,
49
+ "loss": 5.8443,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 4.408396946564885e-05,
55
+ "loss": 4.3173,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.04,
60
+ "learning_rate": 4.980916030534351e-05,
61
+ "loss": 4.7444,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.05,
66
+ "learning_rate": 5.49618320610687e-05,
67
+ "loss": 4.542,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.05,
72
+ "eval_loss": 3.579599618911743,
73
+ "eval_runtime": 132.6751,
74
+ "eval_samples_per_second": 34.822,
75
+ "eval_steps_per_second": 1.093,
76
+ "eval_wer": 1.0,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 0.05,
81
+ "learning_rate": 6.0687022900763354e-05,
82
+ "loss": 3.3873,
83
+ "step": 110
84
+ },
85
+ {
86
+ "epoch": 0.06,
87
+ "learning_rate": 6.641221374045802e-05,
88
+ "loss": 3.1783,
89
+ "step": 120
90
+ },
91
+ {
92
+ "epoch": 0.06,
93
+ "learning_rate": 7.213740458015267e-05,
94
+ "loss": 3.1672,
95
+ "step": 130
96
+ },
97
+ {
98
+ "epoch": 0.06,
99
+ "learning_rate": 7.494113029827315e-05,
100
+ "loss": 3.4915,
101
+ "step": 140
102
+ },
103
+ {
104
+ "epoch": 0.07,
105
+ "learning_rate": 7.483516483516483e-05,
106
+ "loss": 3.7276,
107
+ "step": 150
108
+ },
109
+ {
110
+ "epoch": 0.07,
111
+ "learning_rate": 7.471742543171114e-05,
112
+ "loss": 3.2435,
113
+ "step": 160
114
+ },
115
+ {
116
+ "epoch": 0.08,
117
+ "learning_rate": 7.459968602825744e-05,
118
+ "loss": 3.0634,
119
+ "step": 170
120
+ },
121
+ {
122
+ "epoch": 0.08,
123
+ "learning_rate": 7.448194662480377e-05,
124
+ "loss": 3.0859,
125
+ "step": 180
126
+ },
127
+ {
128
+ "epoch": 0.09,
129
+ "learning_rate": 7.436420722135007e-05,
130
+ "loss": 3.3592,
131
+ "step": 190
132
+ },
133
+ {
134
+ "epoch": 0.09,
135
+ "learning_rate": 7.425824175824176e-05,
136
+ "loss": 3.6018,
137
+ "step": 200
138
+ },
139
+ {
140
+ "epoch": 0.09,
141
+ "eval_loss": 3.3504831790924072,
142
+ "eval_runtime": 130.1255,
143
+ "eval_samples_per_second": 35.504,
144
+ "eval_steps_per_second": 1.114,
145
+ "eval_wer": 1.0,
146
+ "step": 200
147
+ },
148
+ {
149
+ "epoch": 0.1,
150
+ "learning_rate": 7.414050235478806e-05,
151
+ "loss": 3.1612,
152
+ "step": 210
153
+ },
154
+ {
155
+ "epoch": 0.1,
156
+ "learning_rate": 7.402276295133437e-05,
157
+ "loss": 3.0375,
158
+ "step": 220
159
+ },
160
+ {
161
+ "epoch": 0.11,
162
+ "learning_rate": 7.390502354788069e-05,
163
+ "loss": 3.08,
164
+ "step": 230
165
+ },
166
+ {
167
+ "epoch": 0.11,
168
+ "learning_rate": 7.3787284144427e-05,
169
+ "loss": 3.2809,
170
+ "step": 240
171
+ },
172
+ {
173
+ "epoch": 0.12,
174
+ "learning_rate": 7.368131868131867e-05,
175
+ "loss": 3.5351,
176
+ "step": 250
177
+ },
178
+ {
179
+ "epoch": 0.12,
180
+ "learning_rate": 7.356357927786499e-05,
181
+ "loss": 3.01,
182
+ "step": 260
183
+ },
184
+ {
185
+ "epoch": 0.12,
186
+ "learning_rate": 7.34458398744113e-05,
187
+ "loss": 3.0006,
188
+ "step": 270
189
+ },
190
+ {
191
+ "epoch": 0.13,
192
+ "learning_rate": 7.33281004709576e-05,
193
+ "loss": 3.0397,
194
+ "step": 280
195
+ },
196
+ {
197
+ "epoch": 0.13,
198
+ "learning_rate": 7.321036106750392e-05,
199
+ "loss": 3.1733,
200
+ "step": 290
201
+ },
202
+ {
203
+ "epoch": 0.14,
204
+ "learning_rate": 7.310439560439559e-05,
205
+ "loss": 3.5007,
206
+ "step": 300
207
+ },
208
+ {
209
+ "epoch": 0.14,
210
+ "eval_loss": 3.068483591079712,
211
+ "eval_runtime": 129.9806,
212
+ "eval_samples_per_second": 35.544,
213
+ "eval_steps_per_second": 1.116,
214
+ "eval_wer": 1.0,
215
+ "step": 300
216
+ }
217
+ ],
218
+ "max_steps": 6501,
219
+ "num_train_epochs": 3,
220
+ "total_flos": 5.677469874282885e+18,
221
+ "trial_name": null,
222
+ "trial_params": null
223
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad7027bd45ccf9ba552f2894d3dfeae2d3fba8149a74b860da051c61576c8de
3
+ size 3055
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:531ec053d3689e2cee034717172f389cea6d95c0f221d0d68b704b975fc2f325
3
  size 1262067185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68645628512b23e8cf87be35a11a95bbf653c484127f9db2e43ac576589c37b8
3
  size 1262067185