Hugging Face's logo

JRHuy
/
whisper-small-vivos

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JRHuy commited on
Commit
a7af0ed
•
1 Parent(s): 168b70b

Training in progress, step 1000

Browse files
Files changed (15) hide show
  1. .gitignore +1 -0
  2. config.json +152 -0
  3. last-checkpoint/config.json +152 -0
  4. last-checkpoint/generation_config.json +269 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/preprocessor_config.json +14 -0
  7. last-checkpoint/pytorch_model.bin +3 -0
  8. last-checkpoint/rng_state.pth +3 -0
  9. last-checkpoint/scheduler.pt +3 -0
  10. last-checkpoint/trainer_state.json +266 -0
  11. last-checkpoint/training_args.bin +3 -0
  12. preprocessor_config.json +14 -0
  13. pytorch_model.bin +3 -0
  14. runs/Aug20_17-07-13_713cba38a708/events.out.tfevents.1692551245.713cba38a708.95.0 +3 -0
  15. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 12,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50360,
144
+ 50361,
145
+ 50362
146
+ ],
147
+ "torch_dtype": "float32",
148
+ "transformers_version": "4.31.0",
149
+ "use_cache": false,
150
+ "use_weighted_layer_sum": false,
151
+ "vocab_size": 51865
152
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 12,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50360,
144
+ 50361,
145
+ 50362
146
+ ],
147
+ "torch_dtype": "float32",
148
+ "transformers_version": "4.31.0",
149
+ "use_cache": false,
150
+ "use_weighted_layer_sum": false,
151
+ "vocab_size": 51865
152
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,269 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 50278
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ],
60
+ [
61
+ 3,
62
+ 50363
63
+ ]
64
+ ],
65
+ "is_multilingual": true,
66
+ "lang_to_id": {
67
+ "<|af|>": 50327,
68
+ "<|am|>": 50334,
69
+ "<|ar|>": 50272,
70
+ "<|as|>": 50350,
71
+ "<|az|>": 50304,
72
+ "<|ba|>": 50355,
73
+ "<|be|>": 50330,
74
+ "<|bg|>": 50292,
75
+ "<|bn|>": 50302,
76
+ "<|bo|>": 50347,
77
+ "<|br|>": 50309,
78
+ "<|bs|>": 50315,
79
+ "<|ca|>": 50270,
80
+ "<|cs|>": 50283,
81
+ "<|cy|>": 50297,
82
+ "<|da|>": 50285,
83
+ "<|de|>": 50261,
84
+ "<|el|>": 50281,
85
+ "<|en|>": 50259,
86
+ "<|es|>": 50262,
87
+ "<|et|>": 50307,
88
+ "<|eu|>": 50310,
89
+ "<|fa|>": 50300,
90
+ "<|fi|>": 50277,
91
+ "<|fo|>": 50338,
92
+ "<|fr|>": 50265,
93
+ "<|gl|>": 50319,
94
+ "<|gu|>": 50333,
95
+ "<|haw|>": 50352,
96
+ "<|ha|>": 50354,
97
+ "<|he|>": 50279,
98
+ "<|hi|>": 50276,
99
+ "<|hr|>": 50291,
100
+ "<|ht|>": 50339,
101
+ "<|hu|>": 50286,
102
+ "<|hy|>": 50312,
103
+ "<|id|>": 50275,
104
+ "<|is|>": 50311,
105
+ "<|it|>": 50274,
106
+ "<|ja|>": 50266,
107
+ "<|jw|>": 50356,
108
+ "<|ka|>": 50329,
109
+ "<|kk|>": 50316,
110
+ "<|km|>": 50323,
111
+ "<|kn|>": 50306,
112
+ "<|ko|>": 50264,
113
+ "<|la|>": 50294,
114
+ "<|lb|>": 50345,
115
+ "<|ln|>": 50353,
116
+ "<|lo|>": 50336,
117
+ "<|lt|>": 50293,
118
+ "<|lv|>": 50301,
119
+ "<|mg|>": 50349,
120
+ "<|mi|>": 50295,
121
+ "<|mk|>": 50308,
122
+ "<|ml|>": 50296,
123
+ "<|mn|>": 50314,
124
+ "<|mr|>": 50320,
125
+ "<|ms|>": 50282,
126
+ "<|mt|>": 50343,
127
+ "<|my|>": 50346,
128
+ "<|ne|>": 50313,
129
+ "<|nl|>": 50271,
130
+ "<|nn|>": 50342,
131
+ "<|no|>": 50288,
132
+ "<|oc|>": 50328,
133
+ "<|pa|>": 50321,
134
+ "<|pl|>": 50269,
135
+ "<|ps|>": 50340,
136
+ "<|pt|>": 50267,
137
+ "<|ro|>": 50284,
138
+ "<|ru|>": 50263,
139
+ "<|sa|>": 50344,
140
+ "<|sd|>": 50332,
141
+ "<|si|>": 50322,
142
+ "<|sk|>": 50298,
143
+ "<|sl|>": 50305,
144
+ "<|sn|>": 50324,
145
+ "<|so|>": 50326,
146
+ "<|sq|>": 50317,
147
+ "<|sr|>": 50303,
148
+ "<|su|>": 50357,
149
+ "<|sv|>": 50273,
150
+ "<|sw|>": 50318,
151
+ "<|ta|>": 50287,
152
+ "<|te|>": 50299,
153
+ "<|tg|>": 50331,
154
+ "<|th|>": 50289,
155
+ "<|tk|>": 50341,
156
+ "<|tl|>": 50348,
157
+ "<|tr|>": 50268,
158
+ "<|tt|>": 50351,
159
+ "<|uk|>": 50280,
160
+ "<|ur|>": 50290,
161
+ "<|uz|>": 50337,
162
+ "<|vi|>": 50278,
163
+ "<|yi|>": 50335,
164
+ "<|yo|>": 50325,
165
+ "<|zh|>": 50260
166
+ },
167
+ "language": "vietnamese",
168
+ "max_initial_timestamp_index": 1,
169
+ "max_length": 448,
170
+ "no_timestamps_token_id": 50363,
171
+ "pad_token_id": 50257,
172
+ "return_timestamps": false,
173
+ "suppress_tokens": [
174
+ 1,
175
+ 2,
176
+ 7,
177
+ 8,
178
+ 9,
179
+ 10,
180
+ 14,
181
+ 25,
182
+ 26,
183
+ 27,
184
+ 28,
185
+ 29,
186
+ 31,
187
+ 58,
188
+ 59,
189
+ 60,
190
+ 61,
191
+ 62,
192
+ 63,
193
+ 90,
194
+ 91,
195
+ 92,
196
+ 93,
197
+ 359,
198
+ 503,
199
+ 522,
200
+ 542,
201
+ 873,
202
+ 893,
203
+ 902,
204
+ 918,
205
+ 922,
206
+ 931,
207
+ 1350,
208
+ 1853,
209
+ 1982,
210
+ 2460,
211
+ 2627,
212
+ 3246,
213
+ 3253,
214
+ 3268,
215
+ 3536,
216
+ 3846,
217
+ 3961,
218
+ 4183,
219
+ 4667,
220
+ 6585,
221
+ 6647,
222
+ 7273,
223
+ 9061,
224
+ 9383,
225
+ 10428,
226
+ 10929,
227
+ 11938,
228
+ 12033,
229
+ 12331,
230
+ 12562,
231
+ 13793,
232
+ 14157,
233
+ 14635,
234
+ 15265,
235
+ 15618,
236
+ 16553,
237
+ 16604,
238
+ 18362,
239
+ 18956,
240
+ 20075,
241
+ 21675,
242
+ 22520,
243
+ 26130,
244
+ 26161,
245
+ 26435,
246
+ 28279,
247
+ 29464,
248
+ 31650,
249
+ 32302,
250
+ 32470,
251
+ 36865,
252
+ 42863,
253
+ 47425,
254
+ 49870,
255
+ 50254,
256
+ 50258,
257
+ 50358,
258
+ 50359,
259
+ 50360,
260
+ 50361,
261
+ 50362
262
+ ],
263
+ "task": "transcribe",
264
+ "task_to_id": {
265
+ "transcribe": 50359,
266
+ "translate": 50358
267
+ },
268
+ "transformers_version": "4.31.0"
269
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a0364b80d7da28a472b485617d9fd03601e396d96c284dde0cf058c312d114
3
+ size 1934161157
last-checkpoint/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
+ }
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383ebae7d6ef21ae47fd894b8df9f65cfb2f7f9d22e0541de8b6117cf1dea24f
3
+ size 967102729
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a414e764969027db59f536475e679fa837f5cf868456c551dece078e20eb451
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59963924066510fdace06e40de705170e7801273e45f984c4330d09d2783e55d
3
+ size 627
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 20.616420616420616,
3
+ "best_model_checkpoint": "./whisper-small-vivos/checkpoint-1000",
4
+ "epoch": 1.3717421124828533,
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": 0.03,
12
+ "learning_rate": 4.6000000000000004e-07,
13
+ "loss": 3.0428,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.07,
18
+ "learning_rate": 9.600000000000001e-07,
19
+ "loss": 2.6303,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.1,
24
+ "learning_rate": 1.46e-06,
25
+ "loss": 2.0752,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.14,
30
+ "learning_rate": 1.9600000000000003e-06,
31
+ "loss": 1.5733,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.17,
36
+ "learning_rate": 2.46e-06,
37
+ "loss": 1.1017,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.21,
42
+ "learning_rate": 2.96e-06,
43
+ "loss": 0.9,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.24,
48
+ "learning_rate": 3.46e-06,
49
+ "loss": 0.7899,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 0.27,
54
+ "learning_rate": 3.96e-06,
55
+ "loss": 0.6859,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 0.31,
60
+ "learning_rate": 4.4600000000000005e-06,
61
+ "loss": 0.6151,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 0.34,
66
+ "learning_rate": 4.960000000000001e-06,
67
+ "loss": 0.539,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 0.38,
72
+ "learning_rate": 5.460000000000001e-06,
73
+ "loss": 0.37,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 0.41,
78
+ "learning_rate": 5.9600000000000005e-06,
79
+ "loss": 0.3106,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 0.45,
84
+ "learning_rate": 6.460000000000001e-06,
85
+ "loss": 0.2854,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 0.48,
90
+ "learning_rate": 6.96e-06,
91
+ "loss": 0.2651,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 0.51,
96
+ "learning_rate": 7.4600000000000006e-06,
97
+ "loss": 0.2473,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 0.55,
102
+ "learning_rate": 7.960000000000002e-06,
103
+ "loss": 0.2256,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 0.58,
108
+ "learning_rate": 8.46e-06,
109
+ "loss": 0.2195,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 0.62,
114
+ "learning_rate": 8.96e-06,
115
+ "loss": 0.2266,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 0.65,
120
+ "learning_rate": 9.460000000000001e-06,
121
+ "loss": 0.216,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 0.69,
126
+ "learning_rate": 9.960000000000001e-06,
127
+ "loss": 0.2294,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 0.72,
132
+ "learning_rate": 1e-05,
133
+ "loss": 0.1918,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 0.75,
138
+ "learning_rate": 1e-05,
139
+ "loss": 0.2152,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 0.79,
144
+ "learning_rate": 1e-05,
145
+ "loss": 0.187,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 0.82,
150
+ "learning_rate": 1e-05,
151
+ "loss": 0.1756,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 0.86,
156
+ "learning_rate": 1e-05,
157
+ "loss": 0.1862,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 0.89,
162
+ "learning_rate": 1e-05,
163
+ "loss": 0.1744,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 0.93,
168
+ "learning_rate": 1e-05,
169
+ "loss": 0.1764,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 0.96,
174
+ "learning_rate": 1e-05,
175
+ "loss": 0.1662,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 0.99,
180
+ "learning_rate": 1e-05,
181
+ "loss": 0.1788,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 1.03,
186
+ "learning_rate": 1e-05,
187
+ "loss": 0.1472,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 1.06,
192
+ "learning_rate": 1e-05,
193
+ "loss": 0.1381,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 1.1,
198
+ "learning_rate": 1e-05,
199
+ "loss": 0.1277,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 1.13,
204
+ "learning_rate": 1e-05,
205
+ "loss": 0.13,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 1.17,
210
+ "learning_rate": 1e-05,
211
+ "loss": 0.1309,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 1.2,
216
+ "learning_rate": 1e-05,
217
+ "loss": 0.1279,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 1.23,
222
+ "learning_rate": 1e-05,
223
+ "loss": 0.1221,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 1.27,
228
+ "learning_rate": 1e-05,
229
+ "loss": 0.1263,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 1.3,
234
+ "learning_rate": 1e-05,
235
+ "loss": 0.122,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 1.34,
240
+ "learning_rate": 1e-05,
241
+ "loss": 0.1251,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 1.37,
246
+ "learning_rate": 1e-05,
247
+ "loss": 0.1276,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 1.37,
252
+ "eval_cer": 8.6875591223948,
253
+ "eval_loss": 0.21370840072631836,
254
+ "eval_runtime": 393.7923,
255
+ "eval_samples_per_second": 1.93,
256
+ "eval_steps_per_second": 0.122,
257
+ "eval_wer": 20.616420616420616,
258
+ "step": 1000
259
+ }
260
+ ],
261
+ "max_steps": 4000,
262
+ "num_train_epochs": 6,
263
+ "total_flos": 4.61621206351872e+18,
264
+ "trial_name": null,
265
+ "trial_params": null
266
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183b3688d5af801606a749373eb08d97abd31836266567ef26bc14ac7144c015
3
+ size 4155
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 sha256:383ebae7d6ef21ae47fd894b8df9f65cfb2f7f9d22e0541de8b6117cf1dea24f
3
+ size 967102729
runs/Aug20_17-07-13_713cba38a708/events.out.tfevents.1692551245.713cba38a708.95.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21c93fc97b39bff9f20d4451035bbdf4c8cff4a82b54050f17d54a5a22c4597
3
+ size 12474
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183b3688d5af801606a749373eb08d97abd31836266567ef26bc14ac7144c015
3
+ size 4155