GautamR commited on
Commit
871d188
·
1 Parent(s): 8e36894

Add checkpoint 5000

Browse files
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-tiny",
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": 384,
17
+ "decoder_attention_heads": 6,
18
+ "decoder_ffn_dim": 1536,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 4,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 6,
24
+ "encoder_ffn_dim": 1536,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 4,
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": 4,
43
+ "num_mel_bins": 80,
44
+ "pad_token_id": 50257,
45
+ "scale_embedding": false,
46
+ "suppress_tokens": [],
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.41.1",
49
+ "use_cache": true,
50
+ "use_weighted_layer_sum": false,
51
+ "vocab_size": 51865
52
+ }
generation_config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "forced_decoder_ids": [
36
+ [
37
+ 1,
38
+ null
39
+ ],
40
+ [
41
+ 2,
42
+ 50359
43
+ ]
44
+ ],
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
+ "max_initial_timestamp_index": 50,
148
+ "max_length": 448,
149
+ "no_timestamps_token_id": 50363,
150
+ "pad_token_id": 50257,
151
+ "prev_sot_token_id": 50361,
152
+ "return_timestamps": false,
153
+ "suppress_tokens": [
154
+ 1,
155
+ 2,
156
+ 7,
157
+ 8,
158
+ 9,
159
+ 10,
160
+ 14,
161
+ 25,
162
+ 26,
163
+ 27,
164
+ 28,
165
+ 29,
166
+ 31,
167
+ 58,
168
+ 59,
169
+ 60,
170
+ 61,
171
+ 62,
172
+ 63,
173
+ 90,
174
+ 91,
175
+ 92,
176
+ 93,
177
+ 359,
178
+ 503,
179
+ 522,
180
+ 542,
181
+ 873,
182
+ 893,
183
+ 902,
184
+ 918,
185
+ 922,
186
+ 931,
187
+ 1350,
188
+ 1853,
189
+ 1982,
190
+ 2460,
191
+ 2627,
192
+ 3246,
193
+ 3253,
194
+ 3268,
195
+ 3536,
196
+ 3846,
197
+ 3961,
198
+ 4183,
199
+ 4667,
200
+ 6585,
201
+ 6647,
202
+ 7273,
203
+ 9061,
204
+ 9383,
205
+ 10428,
206
+ 10929,
207
+ 11938,
208
+ 12033,
209
+ 12331,
210
+ 12562,
211
+ 13793,
212
+ 14157,
213
+ 14635,
214
+ 15265,
215
+ 15618,
216
+ 16553,
217
+ 16604,
218
+ 18362,
219
+ 18956,
220
+ 20075,
221
+ 21675,
222
+ 22520,
223
+ 26130,
224
+ 26161,
225
+ 26435,
226
+ 28279,
227
+ 29464,
228
+ 31650,
229
+ 32302,
230
+ 32470,
231
+ 36865,
232
+ 42863,
233
+ 47425,
234
+ 49870,
235
+ 50254,
236
+ 50258,
237
+ 50358,
238
+ 50359,
239
+ 50360,
240
+ 50361,
241
+ 50362
242
+ ],
243
+ "task_to_id": {
244
+ "transcribe": 50359,
245
+ "translate": 50358
246
+ },
247
+ "transformers_version": "4.41.1"
248
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d523e3d3e57b040766fd1debe2107a496152a93080d1663b62f806ff44a1773
3
+ size 151061672
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b73ec864179f3f5cac02c8b69fecf252eb0da500a06ac925d5e7b5b7917a3a
3
+ size 297616186
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
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3a2d692a39a4881dc024940998b65c5cfa912d1c903fbd9de274fe80f31f84e
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f64b300da445e2021a07305c183d3c853a52f393afc210dbe723bdaf58c8c5
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 37.030138841855745,
3
+ "best_model_checkpoint": "./whisper-tiny-hi/checkpoint-4500",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 8.432821273803711,
14
+ "learning_rate": 9.920000000000002e-06,
15
+ "loss": 1.1322,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.4738043546676636,
21
+ "eval_runtime": 281.8939,
22
+ "eval_samples_per_second": 1.774,
23
+ "eval_steps_per_second": 1.774,
24
+ "eval_wer": 56.50186251269895,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 7.294736385345459,
30
+ "learning_rate": 9.89979797979798e-06,
31
+ "loss": 0.3933,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.34950900077819824,
37
+ "eval_runtime": 279.7119,
38
+ "eval_samples_per_second": 1.788,
39
+ "eval_steps_per_second": 1.788,
40
+ "eval_wer": 46.79986454453098,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 5.787722587585449,
46
+ "learning_rate": 9.79878787878788e-06,
47
+ "loss": 0.2912,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_loss": 0.3126949667930603,
53
+ "eval_runtime": 279.6788,
54
+ "eval_samples_per_second": 1.788,
55
+ "eval_steps_per_second": 1.788,
56
+ "eval_wer": 43.294954283779205,
57
+ "step": 1500
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 5.6364569664001465,
62
+ "learning_rate": 9.697777777777778e-06,
63
+ "loss": 0.233,
64
+ "step": 2000
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_loss": 0.28942596912384033,
69
+ "eval_runtime": 275.6431,
70
+ "eval_samples_per_second": 1.814,
71
+ "eval_steps_per_second": 1.814,
72
+ "eval_wer": 42.65154080596004,
73
+ "step": 2000
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 5.897181987762451,
78
+ "learning_rate": 9.596767676767677e-06,
79
+ "loss": 0.189,
80
+ "step": 2500
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_loss": 0.2822072207927704,
85
+ "eval_runtime": 276.7489,
86
+ "eval_samples_per_second": 1.807,
87
+ "eval_steps_per_second": 1.807,
88
+ "eval_wer": 42.38062986793092,
89
+ "step": 2500
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 6.849637508392334,
94
+ "learning_rate": 9.495757575757577e-06,
95
+ "loss": 0.1531,
96
+ "step": 3000
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_loss": 0.285165399312973,
101
+ "eval_runtime": 279.3412,
102
+ "eval_samples_per_second": 1.79,
103
+ "eval_steps_per_second": 1.79,
104
+ "eval_wer": 47.13850321706739,
105
+ "step": 3000
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 4.602267265319824,
110
+ "learning_rate": 9.394747474747476e-06,
111
+ "loss": 0.1224,
112
+ "step": 3500
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_loss": 0.29211270809173584,
117
+ "eval_runtime": 280.3174,
118
+ "eval_samples_per_second": 1.784,
119
+ "eval_steps_per_second": 1.784,
120
+ "eval_wer": 51.3376227565188,
121
+ "step": 3500
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "grad_norm": 6.410825729370117,
126
+ "learning_rate": 9.293737373737376e-06,
127
+ "loss": 0.0964,
128
+ "step": 4000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_loss": 0.30172762274742126,
133
+ "eval_runtime": 278.8186,
134
+ "eval_samples_per_second": 1.793,
135
+ "eval_steps_per_second": 1.793,
136
+ "eval_wer": 44.14155096512022,
137
+ "step": 4000
138
+ },
139
+ {
140
+ "epoch": 9.0,
141
+ "grad_norm": 5.8979997634887695,
142
+ "learning_rate": 9.192727272727273e-06,
143
+ "loss": 0.0744,
144
+ "step": 4500
145
+ },
146
+ {
147
+ "epoch": 9.0,
148
+ "eval_loss": 0.31876111030578613,
149
+ "eval_runtime": 278.6007,
150
+ "eval_samples_per_second": 1.795,
151
+ "eval_steps_per_second": 1.795,
152
+ "eval_wer": 37.030138841855745,
153
+ "step": 4500
154
+ }
155
+ ],
156
+ "logging_steps": 500,
157
+ "max_steps": 50000,
158
+ "num_input_tokens_seen": 0,
159
+ "num_train_epochs": 100,
160
+ "save_steps": 500,
161
+ "stateful_callbacks": {
162
+ "TrainerControl": {
163
+ "args": {
164
+ "should_epoch_stop": false,
165
+ "should_evaluate": false,
166
+ "should_log": false,
167
+ "should_save": true,
168
+ "should_training_stop": false
169
+ },
170
+ "attributes": {}
171
+ }
172
+ },
173
+ "total_flos": 1.77255972864e+18,
174
+ "train_batch_size": 16,
175
+ "trial_name": null,
176
+ "trial_params": null
177
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da8644404dde4d2165b24e155ee6be039b05add83500c0c8422d1334ccb91bc6
3
+ size 5240