SamagraDataGov commited on
Commit
af13084
1 Parent(s): 67d38d8

Model save

Browse files
runs/Jun26_13-58-09_bharatsahaiyak-test/events.out.tfevents.1719412660.bharatsahaiyak-test.1356323.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ad4cbfcaf90404aeceb1bd5967d8e61bc8411255d9ae51f8df01db88b5451e
3
+ size 6020
whisper-tiny-hindi-checkpoint-chunk-5/trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 73.71718882303134,
3
+ "best_model_checkpoint": "./whisper-tiny-hindi2_test/checkpoint-120",
4
+ "epoch": 4.920634920634921,
5
+ "eval_steps": 40,
6
+ "global_step": 155,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6349206349206349,
13
+ "grad_norm": Infinity,
14
+ "learning_rate": 2.043269230769231e-06,
15
+ "loss": 3.3856,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 1.2698412698412698,
20
+ "grad_norm": 12.90635871887207,
21
+ "learning_rate": 4.447115384615384e-06,
22
+ "loss": 2.2169,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 1.2698412698412698,
27
+ "eval_loss": 1.7869399785995483,
28
+ "eval_runtime": 509.7564,
29
+ "eval_samples_per_second": 1.962,
30
+ "eval_steps_per_second": 0.49,
31
+ "eval_wer": 241.5580016934801,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 1.9047619047619047,
36
+ "grad_norm": 8.530549049377441,
37
+ "learning_rate": 6.850961538461537e-06,
38
+ "loss": 1.4435,
39
+ "step": 60
40
+ },
41
+ {
42
+ "epoch": 2.5396825396825395,
43
+ "grad_norm": 7.451807022094727,
44
+ "learning_rate": 9.254807692307693e-06,
45
+ "loss": 1.0037,
46
+ "step": 80
47
+ },
48
+ {
49
+ "epoch": 2.5396825396825395,
50
+ "eval_loss": 0.8910112380981445,
51
+ "eval_runtime": 318.2676,
52
+ "eval_samples_per_second": 3.142,
53
+ "eval_steps_per_second": 0.786,
54
+ "eval_wer": 78.55207451312447,
55
+ "step": 80
56
+ },
57
+ {
58
+ "epoch": 3.1746031746031744,
59
+ "grad_norm": 6.283768177032471,
60
+ "learning_rate": 1.1658653846153846e-05,
61
+ "loss": 0.7501,
62
+ "step": 100
63
+ },
64
+ {
65
+ "epoch": 3.8095238095238093,
66
+ "grad_norm": 6.983267307281494,
67
+ "learning_rate": 1.40625e-05,
68
+ "loss": 0.5907,
69
+ "step": 120
70
+ },
71
+ {
72
+ "epoch": 3.8095238095238093,
73
+ "eval_loss": 0.624940812587738,
74
+ "eval_runtime": 318.0146,
75
+ "eval_samples_per_second": 3.145,
76
+ "eval_steps_per_second": 0.786,
77
+ "eval_wer": 73.71718882303134,
78
+ "step": 120
79
+ },
80
+ {
81
+ "epoch": 4.444444444444445,
82
+ "grad_norm": 5.939335346221924,
83
+ "learning_rate": 1.646634615384615e-05,
84
+ "loss": 0.4806,
85
+ "step": 140
86
+ },
87
+ {
88
+ "epoch": 4.920634920634921,
89
+ "step": 155,
90
+ "total_flos": 1.2132186587136e+17,
91
+ "train_loss": 1.3161909626376245,
92
+ "train_runtime": 1802.5104,
93
+ "train_samples_per_second": 2.774,
94
+ "train_steps_per_second": 0.086
95
+ },
96
+ {
97
+ "epoch": 4.920634920634921,
98
+ "step": 155,
99
+ "total_flos": 1.2132186587136e+17,
100
+ "train_loss": 0.0,
101
+ "train_runtime": 0.1541,
102
+ "train_samples_per_second": 32447.028,
103
+ "train_steps_per_second": 1005.858
104
+ },
105
+ {
106
+ "epoch": 4.920634920634921,
107
+ "step": 155,
108
+ "total_flos": 1.2132186587136e+17,
109
+ "train_loss": 0.0,
110
+ "train_runtime": 0.2109,
111
+ "train_samples_per_second": 23707.402,
112
+ "train_steps_per_second": 734.929
113
+ },
114
+ {
115
+ "epoch": 4.920634920634921,
116
+ "step": 155,
117
+ "total_flos": 1.2132186587136e+17,
118
+ "train_loss": 0.0,
119
+ "train_runtime": 0.17,
120
+ "train_samples_per_second": 29405.194,
121
+ "train_steps_per_second": 911.561
122
+ },
123
+ {
124
+ "epoch": 4.920634920634921,
125
+ "step": 155,
126
+ "total_flos": 1.2132186587136e+17,
127
+ "train_loss": 0.0,
128
+ "train_runtime": 0.1766,
129
+ "train_samples_per_second": 28306.956,
130
+ "train_steps_per_second": 877.516
131
+ }
132
+ ],
133
+ "logging_steps": 20,
134
+ "max_steps": 155,
135
+ "num_input_tokens_seen": 0,
136
+ "num_train_epochs": 5,
137
+ "save_steps": 40,
138
+ "stateful_callbacks": {
139
+ "TrainerControl": {
140
+ "args": {
141
+ "should_epoch_stop": false,
142
+ "should_evaluate": false,
143
+ "should_log": false,
144
+ "should_save": true,
145
+ "should_training_stop": false
146
+ },
147
+ "attributes": {}
148
+ }
149
+ },
150
+ "total_flos": 1.2132186587136e+17,
151
+ "train_batch_size": 16,
152
+ "trial_name": null,
153
+ "trial_params": null
154
+ }
whisper-tiny-hindi-checkpoint-chunk-6/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": 0.1,
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
+ }
whisper-tiny-hindi-checkpoint-chunk-6/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
+ }
whisper-tiny-hindi-checkpoint-chunk-6/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
+ }
whisper-tiny-hindi-checkpoint-chunk-6/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be302553c4eadd11f987e45d1a709ba97362714e3d8b3bb19794e15c3d08d52f
3
+ size 151099494
whisper-tiny-hindi-checkpoint-chunk-6/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21be1e79938b339a6279236c12d4ab03a265c6a80902c0f43f588a41011103a2
3
+ size 5240