bakrianoo commited on
Commit
fb2dc12
1 Parent(s): 590c4c5

upload beta version

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 44, "</s>": 45}
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
+ "Wav2Vec2ForPreTraining"
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": 43,
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": "4.16.2",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 46,
106
+ "xvector_output_dim": 512
107
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2720401989ca4dbdc57ad7199cdc4116d02c36c374567e9a1295b01cd6c45b3
3
+ size 625461417
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 sha256:3299e75237418a55c403fc9c78801934d3057ff076e484879bc40bfd516f13ba
3
+ size 1262112241
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39223200ea0fd8350b41518c6492d3d14d96d823ca3f6e9a374864389e6dbb1b
3
+ size 14503
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5091f67e4a1caff5227497b7c37712739cd8baf0783971573e46569913fdfff3
3
+ size 14567
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16de60f262d42506479df2d553aa073b64cf621ae9eebfc35fbc2b23021cee2d
3
+ size 14503
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a641931222bcf2b19d6a073bd70c446b59abafb3a4077c2d6a5aea1f4001e06a
3
+ size 14503
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da3f79cf3a4b4d9379e47a4353e6555235b22515af826d448849df6d7a5f04f0
3
+ size 14567
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16352761baa415d3af2ff3cea0ef555419a76b51449f27bcec56bcdba9a15ff5
3
+ size 14567
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea93d555065f78f93a91b315329c1c392289d935801de6b732e124d18b1586a
3
+ size 14567
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46629c3fa6cb14bd2274cb93b2b9a613c84794d3912a7fb43cf8af9b51524544
3
+ size 14503
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431319fd21daa87636d8253400f763a0a1a5400306ce1db9e67b38942c76551d
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f90f0da980bf8cd346163915335c996f7bbdbcfe93a2e624a8b02f902aa6d01
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/workspace/cv-corpus-8.0-2022-01-19/output", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4493387111903199,
3
+ "best_model_checkpoint": "/workspace/cv-corpus-8.0-2022-01-19/output/checkpoint-1000",
4
+ "epoch": 8.317338451695457,
5
+ "global_step": 13000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.32,
12
+ "learning_rate": 9.92e-05,
13
+ "loss": 6.7916,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.64,
18
+ "learning_rate": 0.00019920000000000002,
19
+ "loss": 1.354,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.64,
24
+ "eval_loss": 0.4108898937702179,
25
+ "eval_runtime": 71.0896,
26
+ "eval_samples_per_second": 146.125,
27
+ "eval_steps_per_second": 1.829,
28
+ "eval_wer": 0.4493387111903199,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.96,
33
+ "learning_rate": 0.00019321941216678059,
34
+ "loss": 0.7084,
35
+ "step": 1500
36
+ },
37
+ {
38
+ "epoch": 1.28,
39
+ "learning_rate": 0.00018638414217361587,
40
+ "loss": 0.5886,
41
+ "step": 2000
42
+ },
43
+ {
44
+ "epoch": 1.28,
45
+ "eval_loss": 0.2797781527042389,
46
+ "eval_runtime": 71.0704,
47
+ "eval_samples_per_second": 146.165,
48
+ "eval_steps_per_second": 1.829,
49
+ "eval_wer": 0.3099334021198762,
50
+ "step": 2000
51
+ },
52
+ {
53
+ "epoch": 1.6,
54
+ "learning_rate": 0.00017954887218045112,
55
+ "loss": 0.5386,
56
+ "step": 2500
57
+ },
58
+ {
59
+ "epoch": 1.92,
60
+ "learning_rate": 0.0001727136021872864,
61
+ "loss": 0.4977,
62
+ "step": 3000
63
+ },
64
+ {
65
+ "epoch": 1.92,
66
+ "eval_loss": 0.23867885768413544,
67
+ "eval_runtime": 71.0833,
68
+ "eval_samples_per_second": 146.138,
69
+ "eval_steps_per_second": 1.829,
70
+ "eval_wer": 0.2673295188068662,
71
+ "step": 3000
72
+ },
73
+ {
74
+ "epoch": 2.24,
75
+ "learning_rate": 0.00016587833219412168,
76
+ "loss": 0.4531,
77
+ "step": 3500
78
+ },
79
+ {
80
+ "epoch": 2.56,
81
+ "learning_rate": 0.00015905673274094328,
82
+ "loss": 0.4253,
83
+ "step": 4000
84
+ },
85
+ {
86
+ "epoch": 2.56,
87
+ "eval_loss": 0.22657370567321777,
88
+ "eval_runtime": 71.5875,
89
+ "eval_samples_per_second": 145.109,
90
+ "eval_steps_per_second": 1.816,
91
+ "eval_wer": 0.2523215458212175,
92
+ "step": 4000
93
+ },
94
+ {
95
+ "epoch": 2.88,
96
+ "learning_rate": 0.00015222146274777856,
97
+ "loss": 0.413,
98
+ "step": 4500
99
+ },
100
+ {
101
+ "epoch": 3.2,
102
+ "learning_rate": 0.0001453861927546138,
103
+ "loss": 0.3942,
104
+ "step": 5000
105
+ },
106
+ {
107
+ "epoch": 3.2,
108
+ "eval_loss": 0.21706202626228333,
109
+ "eval_runtime": 72.0993,
110
+ "eval_samples_per_second": 144.079,
111
+ "eval_steps_per_second": 1.803,
112
+ "eval_wer": 0.2437294812869337,
113
+ "step": 5000
114
+ },
115
+ {
116
+ "epoch": 3.52,
117
+ "learning_rate": 0.00013855092276144907,
118
+ "loss": 0.3741,
119
+ "step": 5500
120
+ },
121
+ {
122
+ "epoch": 3.84,
123
+ "learning_rate": 0.00013171565276828435,
124
+ "loss": 0.3619,
125
+ "step": 6000
126
+ },
127
+ {
128
+ "epoch": 3.84,
129
+ "eval_loss": 0.20762862265110016,
130
+ "eval_runtime": 72.0546,
131
+ "eval_samples_per_second": 144.168,
132
+ "eval_steps_per_second": 1.804,
133
+ "eval_wer": 0.22530719444705,
134
+ "step": 6000
135
+ },
136
+ {
137
+ "epoch": 4.16,
138
+ "learning_rate": 0.00012489405331510595,
139
+ "loss": 0.3435,
140
+ "step": 6500
141
+ },
142
+ {
143
+ "epoch": 4.48,
144
+ "learning_rate": 0.00011805878332194122,
145
+ "loss": 0.3245,
146
+ "step": 7000
147
+ },
148
+ {
149
+ "epoch": 4.48,
150
+ "eval_loss": 0.2087564468383789,
151
+ "eval_runtime": 71.9965,
152
+ "eval_samples_per_second": 144.285,
153
+ "eval_steps_per_second": 1.806,
154
+ "eval_wer": 0.21862864646843636,
155
+ "step": 7000
156
+ },
157
+ {
158
+ "epoch": 4.8,
159
+ "learning_rate": 0.0001112235133287765,
160
+ "loss": 0.3135,
161
+ "step": 7500
162
+ },
163
+ {
164
+ "epoch": 5.12,
165
+ "learning_rate": 0.0001044019138755981,
166
+ "loss": 0.308,
167
+ "step": 8000
168
+ },
169
+ {
170
+ "epoch": 5.12,
171
+ "eval_loss": 0.2086208015680313,
172
+ "eval_runtime": 68.9232,
173
+ "eval_samples_per_second": 150.718,
174
+ "eval_steps_per_second": 1.886,
175
+ "eval_wer": 0.22063596285526685,
176
+ "step": 8000
177
+ },
178
+ {
179
+ "epoch": 5.44,
180
+ "learning_rate": 9.756664388243337e-05,
181
+ "loss": 0.292,
182
+ "step": 8500
183
+ },
184
+ {
185
+ "epoch": 5.76,
186
+ "learning_rate": 9.073137388926864e-05,
187
+ "loss": 0.2881,
188
+ "step": 9000
189
+ },
190
+ {
191
+ "epoch": 5.76,
192
+ "eval_loss": 0.20888157188892365,
193
+ "eval_runtime": 70.2391,
194
+ "eval_samples_per_second": 147.895,
195
+ "eval_steps_per_second": 1.851,
196
+ "eval_wer": 0.21048682112372197,
197
+ "step": 9000
198
+ },
199
+ {
200
+ "epoch": 6.08,
201
+ "learning_rate": 8.389610389610389e-05,
202
+ "loss": 0.2717,
203
+ "step": 9500
204
+ },
205
+ {
206
+ "epoch": 6.4,
207
+ "learning_rate": 7.706083390293917e-05,
208
+ "loss": 0.2557,
209
+ "step": 10000
210
+ },
211
+ {
212
+ "epoch": 6.4,
213
+ "eval_loss": 0.20148096978664398,
214
+ "eval_runtime": 70.1726,
215
+ "eval_samples_per_second": 148.035,
216
+ "eval_steps_per_second": 1.853,
217
+ "eval_wer": 0.20035643935840916,
218
+ "step": 10000
219
+ },
220
+ {
221
+ "epoch": 6.72,
222
+ "learning_rate": 7.022556390977444e-05,
223
+ "loss": 0.2536,
224
+ "step": 10500
225
+ },
226
+ {
227
+ "epoch": 7.04,
228
+ "learning_rate": 6.33902939166097e-05,
229
+ "loss": 0.248,
230
+ "step": 11000
231
+ },
232
+ {
233
+ "epoch": 7.04,
234
+ "eval_loss": 0.2043762356042862,
235
+ "eval_runtime": 70.2184,
236
+ "eval_samples_per_second": 147.938,
237
+ "eval_steps_per_second": 1.851,
238
+ "eval_wer": 0.19529124847575274,
239
+ "step": 11000
240
+ },
241
+ {
242
+ "epoch": 7.36,
243
+ "learning_rate": 5.655502392344498e-05,
244
+ "loss": 0.2308,
245
+ "step": 11500
246
+ },
247
+ {
248
+ "epoch": 7.68,
249
+ "learning_rate": 4.971975393028025e-05,
250
+ "loss": 0.2251,
251
+ "step": 12000
252
+ },
253
+ {
254
+ "epoch": 7.68,
255
+ "eval_loss": 0.20575200021266937,
256
+ "eval_runtime": 70.8946,
257
+ "eval_samples_per_second": 146.527,
258
+ "eval_steps_per_second": 1.834,
259
+ "eval_wer": 0.19315261232529782,
260
+ "step": 12000
261
+ },
262
+ {
263
+ "epoch": 8.0,
264
+ "learning_rate": 4.291182501708818e-05,
265
+ "loss": 0.2207,
266
+ "step": 12500
267
+ },
268
+ {
269
+ "epoch": 8.32,
270
+ "learning_rate": 3.6076555023923446e-05,
271
+ "loss": 0.2052,
272
+ "step": 13000
273
+ },
274
+ {
275
+ "epoch": 8.32,
276
+ "eval_loss": 0.21170856058597565,
277
+ "eval_runtime": 70.7957,
278
+ "eval_samples_per_second": 146.732,
279
+ "eval_steps_per_second": 1.836,
280
+ "eval_wer": 0.18776850201669637,
281
+ "step": 13000
282
+ }
283
+ ],
284
+ "max_steps": 15630,
285
+ "num_train_epochs": 10,
286
+ "total_flos": 8.268631785694088e+20,
287
+ "trial_name": null,
288
+ "trial_params": null
289
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a1b80bcfc69cf9fa9cf637cef6f631649190d0c441246f20b284d86514490bf
3
+ size 3055
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"\"": 1, "،": 2, "ء": 3, "آ": 4, "أ": 5, "ؤ": 6, "إ": 7, "ئ": 8, "ا": 9, "ب": 10, "ة": 11, "ت": 12, "ث": 13, "ج": 14, "ح": 15, "خ": 16, "د": 17, "ذ": 18, "ر": 19, "ز": 20, "س": 21, "ش": 22, "ص": 23, "ض": 24, "ط": 25, "ظ": 26, "ع": 27, "غ": 28, "ـ": 29, "ف": 30, "ق": 31, "ك": 32, "ل": 33, "م": 34, "ن": 35, "ه": 36, "و": 37, "ى": 38, "ي": 39, "ّ": 40, "ی": 41, "|": 0, "[UNK]": 42, "[PAD]": 43}