Hugging Face's logo

aadel4
/
kid-whisper-medium-en-myst

Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
aadel4 commited on
Commit
d613948
•
1 Parent(s): 7eac1e6

Upload 9 files

Browse files
Files changed (9) hide show
  1. config.json +52 -0
  2. generation_config.json +188 -0
  3. optimizer.pt +3 -0
  4. preprocessor_config.json +14 -0
  5. pytorch_model.bin +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. trainer_state.json +136 -0
  9. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-medium.en",
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
+ 50256
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 1024,
17
+ "decoder_attention_heads": 16,
18
+ "decoder_ffn_dim": 4096,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 24,
21
+ "decoder_start_token_id": 50257,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 24,
27
+ "eos_token_id": 50256,
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": 24,
43
+ "num_mel_bins": 80,
44
+ "pad_token_id": 50256,
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": 51864
52
+ }
generation_config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 11,
5
+ 4
6
+ ],
7
+ [
8
+ 14,
9
+ 1
10
+ ],
11
+ [
12
+ 14,
13
+ 12
14
+ ],
15
+ [
16
+ 14,
17
+ 14
18
+ ],
19
+ [
20
+ 15,
21
+ 4
22
+ ],
23
+ [
24
+ 16,
25
+ 0
26
+ ],
27
+ [
28
+ 16,
29
+ 4
30
+ ],
31
+ [
32
+ 16,
33
+ 9
34
+ ],
35
+ [
36
+ 17,
37
+ 12
38
+ ],
39
+ [
40
+ 17,
41
+ 14
42
+ ],
43
+ [
44
+ 18,
45
+ 7
46
+ ],
47
+ [
48
+ 18,
49
+ 10
50
+ ],
51
+ [
52
+ 18,
53
+ 15
54
+ ],
55
+ [
56
+ 20,
57
+ 0
58
+ ],
59
+ [
60
+ 20,
61
+ 3
62
+ ],
63
+ [
64
+ 20,
65
+ 9
66
+ ],
67
+ [
68
+ 20,
69
+ 14
70
+ ],
71
+ [
72
+ 21,
73
+ 12
74
+ ]
75
+ ],
76
+ "begin_suppress_tokens": [
77
+ 220,
78
+ 50256
79
+ ],
80
+ "bos_token_id": 50257,
81
+ "decoder_start_token_id": 50257,
82
+ "eos_token_id": 50256,
83
+ "forced_decoder_ids": [
84
+ [
85
+ 1,
86
+ 50362
87
+ ]
88
+ ],
89
+ "is_multilingual": false,
90
+ "max_initial_timestamp_index": 1,
91
+ "max_length": 448,
92
+ "no_timestamps_token_id": 50362,
93
+ "pad_token_id": 50256,
94
+ "return_timestamps": false,
95
+ "suppress_tokens": [
96
+ 1,
97
+ 2,
98
+ 7,
99
+ 8,
100
+ 9,
101
+ 10,
102
+ 14,
103
+ 25,
104
+ 26,
105
+ 27,
106
+ 28,
107
+ 29,
108
+ 31,
109
+ 58,
110
+ 59,
111
+ 60,
112
+ 61,
113
+ 62,
114
+ 63,
115
+ 90,
116
+ 91,
117
+ 92,
118
+ 93,
119
+ 357,
120
+ 366,
121
+ 438,
122
+ 532,
123
+ 685,
124
+ 705,
125
+ 796,
126
+ 930,
127
+ 1058,
128
+ 1220,
129
+ 1267,
130
+ 1279,
131
+ 1303,
132
+ 1343,
133
+ 1377,
134
+ 1391,
135
+ 1635,
136
+ 1782,
137
+ 1875,
138
+ 2162,
139
+ 2361,
140
+ 2488,
141
+ 3467,
142
+ 4008,
143
+ 4211,
144
+ 4600,
145
+ 4808,
146
+ 5299,
147
+ 5855,
148
+ 6329,
149
+ 7203,
150
+ 9609,
151
+ 9959,
152
+ 10563,
153
+ 10786,
154
+ 11420,
155
+ 11709,
156
+ 11907,
157
+ 13163,
158
+ 13697,
159
+ 13700,
160
+ 14808,
161
+ 15306,
162
+ 16410,
163
+ 16791,
164
+ 17992,
165
+ 19203,
166
+ 19510,
167
+ 20724,
168
+ 22305,
169
+ 22935,
170
+ 27007,
171
+ 30109,
172
+ 30420,
173
+ 33409,
174
+ 34949,
175
+ 40283,
176
+ 40493,
177
+ 40549,
178
+ 47282,
179
+ 49146,
180
+ 50257,
181
+ 50357,
182
+ 50358,
183
+ 50359,
184
+ 50360,
185
+ 50361
186
+ ],
187
+ "transformers_version": "4.32.1"
188
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a0a88962c5ea3f1fcc85483ed0bca578787aa9da65cc96e4ee0ca0f9c759f9
3
+ size 6111655462
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:c7af86b2376f4d0cb6c10774c21b8579dddc50679cd6c779c5796bd20ee58317
3
+ size 3055750873
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:584291ef4756e3af2201f5cfa419912892c3243074900b91d7bdd6ab4287e59b
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26086bd7cdd79710ac8b9404ca1523f677ef8b813284013524b7082e389ca3bb
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 8.26887341422169,
3
+ "best_model_checkpoint": "./fine-tuned-whisper/openai/whisper-medium.en/lr_1e-05_warmup_500_epochs_0_batch_32_grad_acc_1_max_steps_10000/dataset_myst/2023-09-05_18-38-56/checkpoint-500",
4
+ "epoch": 2.4,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
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": 1.9000000000000002e-06,
14
+ "loss": 1.4099,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.32,
19
+ "learning_rate": 3.88e-06,
20
+ "loss": 0.7502,
21
+ "step": 200
22
+ },
23
+ {
24
+ "epoch": 0.48,
25
+ "learning_rate": 5.8800000000000005e-06,
26
+ "loss": 0.5411,
27
+ "step": 300
28
+ },
29
+ {
30
+ "epoch": 0.64,
31
+ "learning_rate": 7.88e-06,
32
+ "loss": 0.4287,
33
+ "step": 400
34
+ },
35
+ {
36
+ "epoch": 0.8,
37
+ "learning_rate": 9.88e-06,
38
+ "loss": 0.4344,
39
+ "step": 500
40
+ },
41
+ {
42
+ "epoch": 0.8,
43
+ "eval_loss": 0.24607381224632263,
44
+ "eval_runtime": 1060.4953,
45
+ "eval_samples_per_second": 2.98,
46
+ "eval_steps_per_second": 0.187,
47
+ "eval_wer": 8.26887341422169,
48
+ "step": 500
49
+ },
50
+ {
51
+ "epoch": 0.96,
52
+ "learning_rate": 9.901052631578948e-06,
53
+ "loss": 0.3805,
54
+ "step": 600
55
+ },
56
+ {
57
+ "epoch": 1.12,
58
+ "learning_rate": 9.795789473684213e-06,
59
+ "loss": 0.3336,
60
+ "step": 700
61
+ },
62
+ {
63
+ "epoch": 1.28,
64
+ "learning_rate": 9.690526315789474e-06,
65
+ "loss": 0.3087,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 1.44,
70
+ "learning_rate": 9.585263157894737e-06,
71
+ "loss": 0.3378,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 1.6,
76
+ "learning_rate": 9.48e-06,
77
+ "loss": 0.3344,
78
+ "step": 1000
79
+ },
80
+ {
81
+ "epoch": 1.6,
82
+ "eval_loss": 0.2452411949634552,
83
+ "eval_runtime": 1073.0532,
84
+ "eval_samples_per_second": 2.945,
85
+ "eval_steps_per_second": 0.185,
86
+ "eval_wer": 8.76847797431891,
87
+ "step": 1000
88
+ },
89
+ {
90
+ "epoch": 1.76,
91
+ "learning_rate": 9.374736842105264e-06,
92
+ "loss": 0.3402,
93
+ "step": 1100
94
+ },
95
+ {
96
+ "epoch": 1.92,
97
+ "learning_rate": 9.269473684210527e-06,
98
+ "loss": 0.3224,
99
+ "step": 1200
100
+ },
101
+ {
102
+ "epoch": 2.08,
103
+ "learning_rate": 9.16421052631579e-06,
104
+ "loss": 0.2762,
105
+ "step": 1300
106
+ },
107
+ {
108
+ "epoch": 2.24,
109
+ "learning_rate": 9.058947368421054e-06,
110
+ "loss": 0.223,
111
+ "step": 1400
112
+ },
113
+ {
114
+ "epoch": 2.4,
115
+ "learning_rate": 8.953684210526317e-06,
116
+ "loss": 0.2329,
117
+ "step": 1500
118
+ },
119
+ {
120
+ "epoch": 2.4,
121
+ "eval_loss": 0.2578390836715698,
122
+ "eval_runtime": 1063.6558,
123
+ "eval_samples_per_second": 2.971,
124
+ "eval_steps_per_second": 0.186,
125
+ "eval_wer": 8.311953858914759,
126
+ "step": 1500
127
+ }
128
+ ],
129
+ "logging_steps": 100,
130
+ "max_steps": 10000,
131
+ "num_train_epochs": 16,
132
+ "save_steps": 500,
133
+ "total_flos": 4.896249983336448e+19,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7c51e83581a36ae1d8d7381bb2b9f4774e22352bbf3004836fe253a2970527
3
+ size 4475