Hugging Face's logo

PereLluis13
/
wav2vec2-large-xlsr-53-greek

Automatic Speech Recognition
Transformers
PyTorch
JAX
Greek
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results
Inference Endpoints
Model card Files Community
1
PereLluis13 commited on
Commit
6c864ef
·
1 Parent(s): 01fcf5b

Add model files

Browse files
Files changed (7) hide show
  1. config.json +76 -0
  2. optimizer.pt +3 -0
  3. preprocessor_config.json +8 -0
  4. pytorch_model.bin +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +240 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/output_models/wav2vec2-large-xlsr-greek/checkpoint-2000",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "conv_bias": true,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "ctc_loss_reduction": "mean",
39
+ "ctc_zero_infinity": false,
40
+ "do_stable_layer_norm": true,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_dropout": 0.0,
44
+ "feat_extract_norm": "layer",
45
+ "feat_proj_dropout": 0.0,
46
+ "final_dropout": 0.0,
47
+ "gradient_checkpointing": true,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_size": 1024,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 4096,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.1,
55
+ "mask_channel_length": 10,
56
+ "mask_channel_min_space": 1,
57
+ "mask_channel_other": 0.0,
58
+ "mask_channel_prob": 0.0,
59
+ "mask_channel_selection": "static",
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_space": 1,
64
+ "mask_time_other": 0.0,
65
+ "mask_time_prob": 0.05,
66
+ "mask_time_selection": "static",
67
+ "model_type": "wav2vec2",
68
+ "num_attention_heads": 16,
69
+ "num_conv_pos_embedding_groups": 16,
70
+ "num_conv_pos_embeddings": 128,
71
+ "num_feat_extract_layers": 7,
72
+ "num_hidden_layers": 24,
73
+ "pad_token_id": 52,
74
+ "transformers_version": "4.5.0.dev0",
75
+ "vocab_size": 53
76
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd35113bf0f1a49c7c50def6bf87ae123b30cd482665fc9c374980062b8346d8
3
+ size 2524210943
preprocessor_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_size": 1,
4
+ "padding_side": "right",
5
+ "padding_value": 0.0,
6
+ "return_attention_mask": true,
7
+ "sampling_rate": 16000
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88cb4a6ec4d0415fc8f06696ae0c3c73d7d2fbc233f3641cfbffba58af8b6e90
3
+ size 1262151127
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac5a342301a9bf886b82a9b938d75f9a7a32cabd40d8c05f577a52e8093d6eab
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 36.7816091954023,
5
+ "global_step": 6400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 3.45,
12
+ "learning_rate": 0.00023999999999999998,
13
+ "loss": NaN,
14
+ "step": 400
15
+ },
16
+ {
17
+ "epoch": 3.45,
18
+ "eval_loss": 3.315488815307617,
19
+ "eval_runtime": 135.9943,
20
+ "eval_samples_per_second": 11.192,
21
+ "eval_wer": 0.9802160088826083,
22
+ "step": 400
23
+ },
24
+ {
25
+ "epoch": 6.89,
26
+ "learning_rate": 0.00025054945054945053,
27
+ "loss": NaN,
28
+ "step": 800
29
+ },
30
+ {
31
+ "epoch": 6.89,
32
+ "eval_loss": 1.239622712135315,
33
+ "eval_runtime": 136.5249,
34
+ "eval_samples_per_second": 11.148,
35
+ "eval_wer": 0.8971434339356011,
36
+ "step": 800
37
+ },
38
+ {
39
+ "epoch": 10.34,
40
+ "learning_rate": 0.0001846153846153846,
41
+ "loss": NaN,
42
+ "step": 1200
43
+ },
44
+ {
45
+ "epoch": 10.34,
46
+ "eval_loss": 0.5218076705932617,
47
+ "eval_runtime": 136.039,
48
+ "eval_samples_per_second": 11.188,
49
+ "eval_wer": 0.5810033309780963,
50
+ "step": 1200
51
+ },
52
+ {
53
+ "epoch": 13.79,
54
+ "learning_rate": 0.00011868131868131866,
55
+ "loss": NaN,
56
+ "step": 1600
57
+ },
58
+ {
59
+ "epoch": 13.79,
60
+ "eval_loss": 0.45067664980888367,
61
+ "eval_runtime": 136.2412,
62
+ "eval_samples_per_second": 11.171,
63
+ "eval_wer": 0.5031795700010094,
64
+ "step": 1600
65
+ },
66
+ {
67
+ "epoch": 17.24,
68
+ "learning_rate": 5.274725274725275e-05,
69
+ "loss": NaN,
70
+ "step": 2000
71
+ },
72
+ {
73
+ "epoch": 17.24,
74
+ "eval_loss": 0.4806972146034241,
75
+ "eval_runtime": 135.9031,
76
+ "eval_samples_per_second": 11.199,
77
+ "eval_wer": 0.48622186332895934,
78
+ "step": 2000
79
+ },
80
+ {
81
+ "epoch": 13.79,
82
+ "learning_rate": 0.00021176470588235295,
83
+ "loss": 1.706,
84
+ "step": 2400
85
+ },
86
+ {
87
+ "epoch": 13.79,
88
+ "eval_loss": 0.4303271174430847,
89
+ "eval_runtime": 143.5562,
90
+ "eval_samples_per_second": 10.602,
91
+ "eval_wer": 0.4874331280912486,
92
+ "step": 2400
93
+ },
94
+ {
95
+ "epoch": 16.09,
96
+ "learning_rate": 0.00019318885448916406,
97
+ "loss": 0.2803,
98
+ "step": 2800
99
+ },
100
+ {
101
+ "epoch": 16.09,
102
+ "eval_loss": 0.39102795720100403,
103
+ "eval_runtime": 144.4788,
104
+ "eval_samples_per_second": 10.534,
105
+ "eval_wer": 0.4415060058544463,
106
+ "step": 2800
107
+ },
108
+ {
109
+ "epoch": 18.39,
110
+ "learning_rate": 0.0001746130030959752,
111
+ "loss": 0.2162,
112
+ "step": 3200
113
+ },
114
+ {
115
+ "epoch": 18.39,
116
+ "eval_loss": 0.3744983971118927,
117
+ "eval_runtime": 146.0666,
118
+ "eval_samples_per_second": 10.42,
119
+ "eval_wer": 0.41728071060866057,
120
+ "step": 3200
121
+ },
122
+ {
123
+ "epoch": 20.69,
124
+ "learning_rate": 0.00015603715170278636,
125
+ "loss": 0.1768,
126
+ "step": 3600
127
+ },
128
+ {
129
+ "epoch": 20.69,
130
+ "eval_loss": 0.4224047064781189,
131
+ "eval_runtime": 145.7761,
132
+ "eval_samples_per_second": 10.441,
133
+ "eval_wer": 0.4194004239426668,
134
+ "step": 3600
135
+ },
136
+ {
137
+ "epoch": 22.99,
138
+ "learning_rate": 0.00013746130030959752,
139
+ "loss": 0.1502,
140
+ "step": 4000
141
+ },
142
+ {
143
+ "epoch": 22.99,
144
+ "eval_loss": 0.37262818217277527,
145
+ "eval_runtime": 145.6131,
146
+ "eval_samples_per_second": 10.452,
147
+ "eval_wer": 0.4009286363177551,
148
+ "step": 4000
149
+ },
150
+ {
151
+ "epoch": 25.29,
152
+ "learning_rate": 0.00011888544891640867,
153
+ "loss": 0.1214,
154
+ "step": 4400
155
+ },
156
+ {
157
+ "epoch": 25.29,
158
+ "eval_loss": 0.3383936583995819,
159
+ "eval_runtime": 146.7077,
160
+ "eval_samples_per_second": 10.374,
161
+ "eval_wer": 0.3776117896436863,
162
+ "step": 4400
163
+ },
164
+ {
165
+ "epoch": 27.59,
166
+ "learning_rate": 0.00010030959752321979,
167
+ "loss": 0.105,
168
+ "step": 4800
169
+ },
170
+ {
171
+ "epoch": 27.59,
172
+ "eval_loss": 0.3606471121311188,
173
+ "eval_runtime": 146.6063,
174
+ "eval_samples_per_second": 10.382,
175
+ "eval_wer": 0.3755930150398708,
176
+ "step": 4800
177
+ },
178
+ {
179
+ "epoch": 29.89,
180
+ "learning_rate": 8.173374613003094e-05,
181
+ "loss": 0.0917,
182
+ "step": 5200
183
+ },
184
+ {
185
+ "epoch": 29.89,
186
+ "eval_loss": 0.35728928446769714,
187
+ "eval_runtime": 147.1176,
188
+ "eval_samples_per_second": 10.345,
189
+ "eval_wer": 0.3658019582113657,
190
+ "step": 5200
191
+ },
192
+ {
193
+ "epoch": 32.18,
194
+ "learning_rate": 6.315789473684209e-05,
195
+ "loss": 0.0782,
196
+ "step": 5600
197
+ },
198
+ {
199
+ "epoch": 32.18,
200
+ "eval_loss": 0.36559608578681946,
201
+ "eval_runtime": 148.3984,
202
+ "eval_samples_per_second": 10.256,
203
+ "eval_wer": 0.3630766124962148,
204
+ "step": 5600
205
+ },
206
+ {
207
+ "epoch": 34.48,
208
+ "learning_rate": 4.4582043343653246e-05,
209
+ "loss": 0.0713,
210
+ "step": 6000
211
+ },
212
+ {
213
+ "epoch": 34.48,
214
+ "eval_loss": 0.3449805676937103,
215
+ "eval_runtime": 147.7614,
216
+ "eval_samples_per_second": 10.3,
217
+ "eval_wer": 0.35611184011305136,
218
+ "step": 6000
219
+ },
220
+ {
221
+ "epoch": 36.78,
222
+ "learning_rate": 2.6006191950464395e-05,
223
+ "loss": 0.0666,
224
+ "step": 6400
225
+ },
226
+ {
227
+ "epoch": 36.78,
228
+ "eval_loss": 0.3429848849773407,
229
+ "eval_runtime": 147.6625,
230
+ "eval_samples_per_second": 10.307,
231
+ "eval_wer": 0.3475320480468356,
232
+ "step": 6400
233
+ }
234
+ ],
235
+ "max_steps": 6960,
236
+ "num_train_epochs": 40,
237
+ "total_flos": 3.238027552454268e+19,
238
+ "trial_name": null,
239
+ "trial_params": null
240
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d2a87e65db4435d4a64848837b81df3ed5c9a2c4d0e8188a6fd131d40e17fb
3
+ size 2351