thak123 commited on
Commit
fdb0b26
1 Parent(s): 08bc9a2

Upload 9 files

Browse files
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_type": "whisper",
41
+ "num_hidden_layers": 12,
42
+ "num_mel_bins": 80,
43
+ "pad_token_id": 50257,
44
+ "scale_embedding": false,
45
+ "suppress_tokens": [],
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.28.1",
48
+ "use_cache": true,
49
+ "use_weighted_layer_sum": false,
50
+ "vocab_size": 51865
51
+ }
generation_config.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "begin_suppress_tokens": [
3
+ 220,
4
+ 50257
5
+ ],
6
+ "bos_token_id": 50257,
7
+ "decoder_start_token_id": 50258,
8
+ "eos_token_id": 50257,
9
+ "forced_decoder_ids": [
10
+ [
11
+ 1,
12
+ null
13
+ ],
14
+ [
15
+ 2,
16
+ 50359
17
+ ]
18
+ ],
19
+ "is_multilingual": true,
20
+ "lang_to_id": {
21
+ "<|af|>": 50327,
22
+ "<|am|>": 50334,
23
+ "<|ar|>": 50272,
24
+ "<|as|>": 50350,
25
+ "<|az|>": 50304,
26
+ "<|ba|>": 50355,
27
+ "<|be|>": 50330,
28
+ "<|bg|>": 50292,
29
+ "<|bn|>": 50302,
30
+ "<|bo|>": 50347,
31
+ "<|br|>": 50309,
32
+ "<|bs|>": 50315,
33
+ "<|ca|>": 50270,
34
+ "<|cs|>": 50283,
35
+ "<|cy|>": 50297,
36
+ "<|da|>": 50285,
37
+ "<|de|>": 50261,
38
+ "<|el|>": 50281,
39
+ "<|en|>": 50259,
40
+ "<|es|>": 50262,
41
+ "<|et|>": 50307,
42
+ "<|eu|>": 50310,
43
+ "<|fa|>": 50300,
44
+ "<|fi|>": 50277,
45
+ "<|fo|>": 50338,
46
+ "<|fr|>": 50265,
47
+ "<|gl|>": 50319,
48
+ "<|gu|>": 50333,
49
+ "<|haw|>": 50352,
50
+ "<|ha|>": 50354,
51
+ "<|he|>": 50279,
52
+ "<|hi|>": 50276,
53
+ "<|hr|>": 50291,
54
+ "<|ht|>": 50339,
55
+ "<|hu|>": 50286,
56
+ "<|hy|>": 50312,
57
+ "<|id|>": 50275,
58
+ "<|is|>": 50311,
59
+ "<|it|>": 50274,
60
+ "<|ja|>": 50266,
61
+ "<|jw|>": 50356,
62
+ "<|ka|>": 50329,
63
+ "<|kk|>": 50316,
64
+ "<|km|>": 50323,
65
+ "<|kn|>": 50306,
66
+ "<|ko|>": 50264,
67
+ "<|la|>": 50294,
68
+ "<|lb|>": 50345,
69
+ "<|ln|>": 50353,
70
+ "<|lo|>": 50336,
71
+ "<|lt|>": 50293,
72
+ "<|lv|>": 50301,
73
+ "<|mg|>": 50349,
74
+ "<|mi|>": 50295,
75
+ "<|mk|>": 50308,
76
+ "<|ml|>": 50296,
77
+ "<|mn|>": 50314,
78
+ "<|mr|>": 50320,
79
+ "<|ms|>": 50282,
80
+ "<|mt|>": 50343,
81
+ "<|my|>": 50346,
82
+ "<|ne|>": 50313,
83
+ "<|nl|>": 50271,
84
+ "<|nn|>": 50342,
85
+ "<|no|>": 50288,
86
+ "<|oc|>": 50328,
87
+ "<|pa|>": 50321,
88
+ "<|pl|>": 50269,
89
+ "<|ps|>": 50340,
90
+ "<|pt|>": 50267,
91
+ "<|ro|>": 50284,
92
+ "<|ru|>": 50263,
93
+ "<|sa|>": 50344,
94
+ "<|sd|>": 50332,
95
+ "<|si|>": 50322,
96
+ "<|sk|>": 50298,
97
+ "<|sl|>": 50305,
98
+ "<|sn|>": 50324,
99
+ "<|so|>": 50326,
100
+ "<|sq|>": 50317,
101
+ "<|sr|>": 50303,
102
+ "<|su|>": 50357,
103
+ "<|sv|>": 50273,
104
+ "<|sw|>": 50318,
105
+ "<|ta|>": 50287,
106
+ "<|te|>": 50299,
107
+ "<|tg|>": 50331,
108
+ "<|th|>": 50289,
109
+ "<|tk|>": 50341,
110
+ "<|tl|>": 50348,
111
+ "<|tr|>": 50268,
112
+ "<|tt|>": 50351,
113
+ "<|uk|>": 50280,
114
+ "<|ur|>": 50290,
115
+ "<|uz|>": 50337,
116
+ "<|vi|>": 50278,
117
+ "<|yi|>": 50335,
118
+ "<|yo|>": 50325,
119
+ "<|zh|>": 50260
120
+ },
121
+ "max_initial_timestamp_index": 1,
122
+ "max_length": 448,
123
+ "no_timestamps_token_id": 50363,
124
+ "pad_token_id": 50257,
125
+ "return_timestamps": false,
126
+ "suppress_tokens": [
127
+ 1,
128
+ 2,
129
+ 7,
130
+ 8,
131
+ 9,
132
+ 10,
133
+ 14,
134
+ 25,
135
+ 26,
136
+ 27,
137
+ 28,
138
+ 29,
139
+ 31,
140
+ 58,
141
+ 59,
142
+ 60,
143
+ 61,
144
+ 62,
145
+ 63,
146
+ 90,
147
+ 91,
148
+ 92,
149
+ 93,
150
+ 359,
151
+ 503,
152
+ 522,
153
+ 542,
154
+ 873,
155
+ 893,
156
+ 902,
157
+ 918,
158
+ 922,
159
+ 931,
160
+ 1350,
161
+ 1853,
162
+ 1982,
163
+ 2460,
164
+ 2627,
165
+ 3246,
166
+ 3253,
167
+ 3268,
168
+ 3536,
169
+ 3846,
170
+ 3961,
171
+ 4183,
172
+ 4667,
173
+ 6585,
174
+ 6647,
175
+ 7273,
176
+ 9061,
177
+ 9383,
178
+ 10428,
179
+ 10929,
180
+ 11938,
181
+ 12033,
182
+ 12331,
183
+ 12562,
184
+ 13793,
185
+ 14157,
186
+ 14635,
187
+ 15265,
188
+ 15618,
189
+ 16553,
190
+ 16604,
191
+ 18362,
192
+ 18956,
193
+ 20075,
194
+ 21675,
195
+ 22520,
196
+ 26130,
197
+ 26161,
198
+ 26435,
199
+ 28279,
200
+ 29464,
201
+ 31650,
202
+ 32302,
203
+ 32470,
204
+ 36865,
205
+ 42863,
206
+ 47425,
207
+ 49870,
208
+ 50254,
209
+ 50258,
210
+ 50358,
211
+ 50359,
212
+ 50360,
213
+ 50361,
214
+ 50362
215
+ ],
216
+ "task_to_id": {
217
+ "transcribe": 50359,
218
+ "translate": 50358
219
+ },
220
+ "transformers_version": "4.28.1"
221
+ }
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:d6f52bea90b7125d2e3d67a0cc80195f887ad26bb285afbd9dc256ac43aece13
3
+ size 967102601
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2620c3dc0dd9765ee9b8039148ae6f86d415091bcc794cf46ac3dfc5178bfffb
3
+ size 14575
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26dbe439de3dd73741374b46df74ee981e9ad3b04a0c5c8a564c625a65b8aee5
3
+ size 557
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90dd2338805bd3a69fa663686537f5e5065d09a0615f56ffc3e4278e4e48b9dd
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 99.95633187772926,
3
+ "best_model_checkpoint": "./whisper-small-gom/checkpoint-1000",
4
+ "epoch": 1.41643059490085,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 4.6000000000000004e-07,
13
+ "loss": 2.481,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.07,
18
+ "learning_rate": 9.600000000000001e-07,
19
+ "loss": 2.0967,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.11,
24
+ "learning_rate": 1.46e-06,
25
+ "loss": 1.8738,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.14,
30
+ "learning_rate": 1.9600000000000003e-06,
31
+ "loss": 1.5778,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.18,
36
+ "learning_rate": 2.46e-06,
37
+ "loss": 1.5275,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.21,
42
+ "learning_rate": 2.96e-06,
43
+ "loss": 1.4266,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.25,
48
+ "learning_rate": 3.46e-06,
49
+ "loss": 1.3163,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 0.28,
54
+ "learning_rate": 3.96e-06,
55
+ "loss": 1.3454,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 0.32,
60
+ "learning_rate": 4.4600000000000005e-06,
61
+ "loss": 1.248,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 0.35,
66
+ "learning_rate": 4.960000000000001e-06,
67
+ "loss": 1.2251,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 0.39,
72
+ "learning_rate": 5.460000000000001e-06,
73
+ "loss": 1.2044,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 0.42,
78
+ "learning_rate": 5.9600000000000005e-06,
79
+ "loss": 1.1433,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 0.46,
84
+ "learning_rate": 6.460000000000001e-06,
85
+ "loss": 1.1663,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 0.5,
90
+ "learning_rate": 6.96e-06,
91
+ "loss": 1.1463,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 0.53,
96
+ "learning_rate": 7.4600000000000006e-06,
97
+ "loss": 1.0479,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 0.57,
102
+ "learning_rate": 7.960000000000002e-06,
103
+ "loss": 1.0869,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 0.6,
108
+ "learning_rate": 8.46e-06,
109
+ "loss": 1.0555,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 0.64,
114
+ "learning_rate": 8.96e-06,
115
+ "loss": 0.9438,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 0.67,
120
+ "learning_rate": 9.460000000000001e-06,
121
+ "loss": 0.9683,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 0.71,
126
+ "learning_rate": 9.960000000000001e-06,
127
+ "loss": 0.9701,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 0.74,
132
+ "learning_rate": 9.934285714285715e-06,
133
+ "loss": 0.9346,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 0.78,
138
+ "learning_rate": 9.862857142857144e-06,
139
+ "loss": 0.959,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 0.81,
144
+ "learning_rate": 9.791428571428571e-06,
145
+ "loss": 0.8805,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 0.85,
150
+ "learning_rate": 9.72e-06,
151
+ "loss": 0.8644,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 0.89,
156
+ "learning_rate": 9.648571428571429e-06,
157
+ "loss": 0.8948,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 0.92,
162
+ "learning_rate": 9.577142857142858e-06,
163
+ "loss": 0.9455,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 0.96,
168
+ "learning_rate": 9.505714285714287e-06,
169
+ "loss": 0.8696,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 0.99,
174
+ "learning_rate": 9.434285714285714e-06,
175
+ "loss": 0.8829,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 1.03,
180
+ "learning_rate": 9.362857142857143e-06,
181
+ "loss": 0.7547,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 1.06,
186
+ "learning_rate": 9.291428571428572e-06,
187
+ "loss": 0.815,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 1.1,
192
+ "learning_rate": 9.220000000000002e-06,
193
+ "loss": 0.8324,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 1.13,
198
+ "learning_rate": 9.148571428571429e-06,
199
+ "loss": 0.7684,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 1.17,
204
+ "learning_rate": 9.077142857142858e-06,
205
+ "loss": 0.7822,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 1.2,
210
+ "learning_rate": 9.005714285714287e-06,
211
+ "loss": 0.7616,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 1.24,
216
+ "learning_rate": 8.934285714285716e-06,
217
+ "loss": 0.8268,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 1.27,
222
+ "learning_rate": 8.862857142857143e-06,
223
+ "loss": 0.8051,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 1.31,
228
+ "learning_rate": 8.791428571428572e-06,
229
+ "loss": 0.804,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 1.35,
234
+ "learning_rate": 8.720000000000001e-06,
235
+ "loss": 0.7387,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 1.38,
240
+ "learning_rate": 8.64857142857143e-06,
241
+ "loss": 0.7993,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 1.42,
246
+ "learning_rate": 8.577142857142858e-06,
247
+ "loss": 0.8099,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 1.42,
252
+ "eval_loss": 0.8143458366394043,
253
+ "eval_runtime": 1609.901,
254
+ "eval_samples_per_second": 1.238,
255
+ "eval_steps_per_second": 0.155,
256
+ "eval_wer": 99.95633187772926,
257
+ "step": 1000
258
+ }
259
+ ],
260
+ "max_steps": 4000,
261
+ "num_train_epochs": 6,
262
+ "total_flos": 4.6159234781184e+18,
263
+ "trial_name": null,
264
+ "trial_params": null
265
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d0542ecab23674b7c03434081710f0fb270c142a842031984047ea9c793cf7
3
+ size 3771