aadel4 commited on
Commit
c46adfd
1 Parent(s): c07879e

Upload 9 files

Browse files
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": null,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
+ "max_length": 448,
38
+ "max_source_positions": 1500,
39
+ "max_target_positions": 448,
40
+ "median_filter_width": 7,
41
+ "model_type": "whisper",
42
+ "num_hidden_layers": 12,
43
+ "num_mel_bins": 80,
44
+ "pad_token_id": 50257,
45
+ "scale_embedding": false,
46
+ "suppress_tokens": [],
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.32.1",
49
+ "use_cache": false,
50
+ "use_weighted_layer_sum": false,
51
+ "vocab_size": 51865
52
+ }
generation_config.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
42
+ ]
43
+ ],
44
+ "begin_suppress_tokens": [
45
+ 220,
46
+ 50257
47
+ ],
48
+ "bos_token_id": 50257,
49
+ "decoder_start_token_id": 50258,
50
+ "eos_token_id": 50257,
51
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|zh|>": 50260
162
+ },
163
+ "max_initial_timestamp_index": 1,
164
+ "max_length": 448,
165
+ "no_timestamps_token_id": 50363,
166
+ "pad_token_id": 50257,
167
+ "return_timestamps": false,
168
+ "suppress_tokens": [
169
+ 1,
170
+ 2,
171
+ 7,
172
+ 8,
173
+ 9,
174
+ 10,
175
+ 14,
176
+ 25,
177
+ 26,
178
+ 27,
179
+ 28,
180
+ 29,
181
+ 31,
182
+ 58,
183
+ 59,
184
+ 60,
185
+ 61,
186
+ 62,
187
+ 63,
188
+ 90,
189
+ 91,
190
+ 92,
191
+ 93,
192
+ 359,
193
+ 503,
194
+ 522,
195
+ 542,
196
+ 873,
197
+ 893,
198
+ 902,
199
+ 918,
200
+ 922,
201
+ 931,
202
+ 1350,
203
+ 1853,
204
+ 1982,
205
+ 2460,
206
+ 2627,
207
+ 3246,
208
+ 3253,
209
+ 3268,
210
+ 3536,
211
+ 3846,
212
+ 3961,
213
+ 4183,
214
+ 4667,
215
+ 6585,
216
+ 6647,
217
+ 7273,
218
+ 9061,
219
+ 9383,
220
+ 10428,
221
+ 10929,
222
+ 11938,
223
+ 12033,
224
+ 12331,
225
+ 12562,
226
+ 13793,
227
+ 14157,
228
+ 14635,
229
+ 15265,
230
+ 15618,
231
+ 16553,
232
+ 16604,
233
+ 18362,
234
+ 18956,
235
+ 20075,
236
+ 21675,
237
+ 22520,
238
+ 26130,
239
+ 26161,
240
+ 26435,
241
+ 28279,
242
+ 29464,
243
+ 31650,
244
+ 32302,
245
+ 32470,
246
+ 36865,
247
+ 42863,
248
+ 47425,
249
+ 49870,
250
+ 50254,
251
+ 50258,
252
+ 50358,
253
+ 50359,
254
+ 50360,
255
+ 50361,
256
+ 50362
257
+ ],
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "transformers_version": "4.32.1"
263
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306496dad270084c23de1fa731487b3fcdef625042ae0b0d56592a148dea2597
3
+ size 1934280442
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4c01ab3a012d217948cb016a6e9780361162a68f664050ee37575ee6176257
3
+ size 967102729
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94db8b0ca9b3a76b8f8afdd48424eda87548662ef7475e3d124b30ea3f89d6cd
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79f6b93f3039d3a115866a80b1a0fc3ef9cfce030a4d23c8f50f865a7e737b1
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 9.06746912032304,
3
+ "best_model_checkpoint": "./fine-tuned-whisper/openai/whisper-small/lr_1e-05_warmup_500_epochs_0_batch_32_grad_acc_1_max_steps_10000/dataset_myst/2023-09-09_11-20-19/checkpoint-1500",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "learning_rate": 1.94e-06,
14
+ "loss": 1.7092,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.32,
19
+ "learning_rate": 3.94e-06,
20
+ "loss": 0.6661,
21
+ "step": 200
22
+ },
23
+ {
24
+ "epoch": 0.48,
25
+ "learning_rate": 5.94e-06,
26
+ "loss": 0.4875,
27
+ "step": 300
28
+ },
29
+ {
30
+ "epoch": 0.64,
31
+ "learning_rate": 7.94e-06,
32
+ "loss": 0.4176,
33
+ "step": 400
34
+ },
35
+ {
36
+ "epoch": 0.8,
37
+ "learning_rate": 9.940000000000001e-06,
38
+ "loss": 0.3943,
39
+ "step": 500
40
+ },
41
+ {
42
+ "epoch": 0.8,
43
+ "eval_loss": 0.23756489157676697,
44
+ "eval_runtime": 611.1384,
45
+ "eval_samples_per_second": 5.171,
46
+ "eval_steps_per_second": 0.324,
47
+ "eval_wer": 10.145123229361573,
48
+ "step": 500
49
+ },
50
+ {
51
+ "epoch": 0.96,
52
+ "learning_rate": 9.897894736842107e-06,
53
+ "loss": 0.3814,
54
+ "step": 600
55
+ },
56
+ {
57
+ "epoch": 1.12,
58
+ "learning_rate": 9.79263157894737e-06,
59
+ "loss": 0.3181,
60
+ "step": 700
61
+ },
62
+ {
63
+ "epoch": 1.28,
64
+ "learning_rate": 9.687368421052632e-06,
65
+ "loss": 0.3291,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 1.44,
70
+ "learning_rate": 9.582105263157897e-06,
71
+ "loss": 0.324,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 1.6,
76
+ "learning_rate": 9.476842105263158e-06,
77
+ "loss": 0.3302,
78
+ "step": 1000
79
+ },
80
+ {
81
+ "epoch": 1.6,
82
+ "eval_loss": 0.22787314653396606,
83
+ "eval_runtime": 601.1188,
84
+ "eval_samples_per_second": 5.257,
85
+ "eval_steps_per_second": 0.329,
86
+ "eval_wer": 9.153630009709175,
87
+ "step": 1000
88
+ },
89
+ {
90
+ "epoch": 1.76,
91
+ "learning_rate": 9.371578947368421e-06,
92
+ "loss": 0.3232,
93
+ "step": 1100
94
+ },
95
+ {
96
+ "epoch": 1.92,
97
+ "learning_rate": 9.266315789473685e-06,
98
+ "loss": 0.3179,
99
+ "step": 1200
100
+ },
101
+ {
102
+ "epoch": 2.08,
103
+ "learning_rate": 9.161052631578948e-06,
104
+ "loss": 0.2809,
105
+ "step": 1300
106
+ },
107
+ {
108
+ "epoch": 2.24,
109
+ "learning_rate": 9.055789473684211e-06,
110
+ "loss": 0.2445,
111
+ "step": 1400
112
+ },
113
+ {
114
+ "epoch": 2.4,
115
+ "learning_rate": 8.950526315789474e-06,
116
+ "loss": 0.2523,
117
+ "step": 1500
118
+ },
119
+ {
120
+ "epoch": 2.4,
121
+ "eval_loss": 0.23648202419281006,
122
+ "eval_runtime": 599.2062,
123
+ "eval_samples_per_second": 5.274,
124
+ "eval_steps_per_second": 0.33,
125
+ "eval_wer": 9.06746912032304,
126
+ "step": 1500
127
+ },
128
+ {
129
+ "epoch": 2.56,
130
+ "learning_rate": 8.845263157894738e-06,
131
+ "loss": 0.2481,
132
+ "step": 1600
133
+ },
134
+ {
135
+ "epoch": 2.72,
136
+ "learning_rate": 8.740000000000001e-06,
137
+ "loss": 0.2596,
138
+ "step": 1700
139
+ },
140
+ {
141
+ "epoch": 2.88,
142
+ "learning_rate": 8.634736842105264e-06,
143
+ "loss": 0.256,
144
+ "step": 1800
145
+ },
146
+ {
147
+ "epoch": 3.04,
148
+ "learning_rate": 8.529473684210528e-06,
149
+ "loss": 0.2419,
150
+ "step": 1900
151
+ },
152
+ {
153
+ "epoch": 3.2,
154
+ "learning_rate": 8.42421052631579e-06,
155
+ "loss": 0.1874,
156
+ "step": 2000
157
+ },
158
+ {
159
+ "epoch": 3.2,
160
+ "eval_loss": 0.24421058595180511,
161
+ "eval_runtime": 604.8436,
162
+ "eval_samples_per_second": 5.224,
163
+ "eval_steps_per_second": 0.327,
164
+ "eval_wer": 9.441690296612077,
165
+ "step": 2000
166
+ },
167
+ {
168
+ "epoch": 3.36,
169
+ "learning_rate": 8.318947368421052e-06,
170
+ "loss": 0.1942,
171
+ "step": 2100
172
+ },
173
+ {
174
+ "epoch": 3.52,
175
+ "learning_rate": 8.213684210526316e-06,
176
+ "loss": 0.2072,
177
+ "step": 2200
178
+ },
179
+ {
180
+ "epoch": 3.68,
181
+ "learning_rate": 8.10842105263158e-06,
182
+ "loss": 0.1809,
183
+ "step": 2300
184
+ },
185
+ {
186
+ "epoch": 3.84,
187
+ "learning_rate": 8.003157894736842e-06,
188
+ "loss": 0.1791,
189
+ "step": 2400
190
+ },
191
+ {
192
+ "epoch": 4.0,
193
+ "learning_rate": 7.897894736842106e-06,
194
+ "loss": 0.2087,
195
+ "step": 2500
196
+ },
197
+ {
198
+ "epoch": 4.0,
199
+ "eval_loss": 0.2534370422363281,
200
+ "eval_runtime": 605.6058,
201
+ "eval_samples_per_second": 5.218,
202
+ "eval_steps_per_second": 0.327,
203
+ "eval_wer": 9.089973830237328,
204
+ "step": 2500
205
+ }
206
+ ],
207
+ "logging_steps": 100,
208
+ "max_steps": 10000,
209
+ "num_train_epochs": 16,
210
+ "save_steps": 500,
211
+ "total_flos": 2.307182558478336e+19,
212
+ "trial_name": null,
213
+ "trial_params": null
214
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef39cb81af4cc7425acfda9f9b25145130b148d5af98d3dfa917b4343e5944c1
3
+ size 4411