Hugging Face's logo

vsro200
/
whisper-small-vsro200

Automatic Speech Recognition
Transformers
Safetensors
Romanian
whisper
Generated from Trainer
speech-recognition
romanian
noisy-speech
avsr
audio-visual-speech-recognition
Model card Files
xet
 Community
vsro200 commited on
Commit
ec9aec7
·
verified ·
1 Parent(s): e3013e1

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. README.md +58 -0
  2. config.json +47 -0
  3. generation_config.json +24 -0
  4. last-checkpoint/config.json +47 -0
  5. last-checkpoint/generation_config.json +24 -0
  6. last-checkpoint/model.safetensors +3 -0
  7. last-checkpoint/optimizer.pt +3 -0
  8. last-checkpoint/preprocessor_config.json +14 -0
  9. last-checkpoint/rng_state.pth +3 -0
  10. last-checkpoint/scaler.pt +3 -0
  11. last-checkpoint/scheduler.pt +3 -0
  12. last-checkpoint/trainer_state.json +524 -0
  13. last-checkpoint/training_args.bin +3 -0
  14. model.safetensors +3 -0
  15. preprocessor_config.json +14 -0
  16. processor_config.json +17 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +128 -0
  19. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: alexandradiaconu/whisper-small-echo-34
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: whisper-small-ro-noisy
8
+ results: []
9
+ datasets:
10
+ - iulik-pisik/ro_vsr
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # whisper-small-ro-noisy
17
+
18
+ This model is a fine-tuned version of [alexandradiaconu/whisper-small-echo-34](https://huggingface.co/alexandradiaconu/whisper-small-echo-34) on an unknown dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 32
43
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 100
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 5.0.0
56
+ - Pytorch 2.10.0+cu128
57
+ - Datasets 4.0.0
58
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 768,
12
+ "decoder_attention_heads": 12,
13
+ "decoder_ffn_dim": 3072,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 12,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 12,
20
+ "encoder_ffn_dim": 3072,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 12,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": null,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "mask_feature_length": 10,
28
+ "mask_feature_min_masks": 0,
29
+ "mask_feature_prob": 0.0,
30
+ "mask_time_length": 10,
31
+ "mask_time_min_masks": 2,
32
+ "mask_time_prob": 0.05,
33
+ "max_source_positions": 1500,
34
+ "max_target_positions": 448,
35
+ "median_filter_width": 7,
36
+ "model_type": "whisper",
37
+ "num_hidden_layers": 12,
38
+ "num_mel_bins": 80,
39
+ "pad_token_id": 50257,
40
+ "scale_embedding": false,
41
+ "suppress_tokens": null,
42
+ "tie_word_embeddings": true,
43
+ "transformers_version": "5.0.0",
44
+ "use_cache": false,
45
+ "use_weighted_layer_sum": false,
46
+ "vocab_size": 51865
47
+ }
generation_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50257,
4
+ "decoder_start_token_id": 50258,
5
+ "eos_token_id": 50257,
6
+ "forced_decoder_ids": [
7
+ [
8
+ 1,
9
+ 50284
10
+ ],
11
+ [
12
+ 2,
13
+ 50359
14
+ ],
15
+ [
16
+ 3,
17
+ 50363
18
+ ]
19
+ ],
20
+ "pad_token_id": 50257,
21
+ "suppress_tokens": [],
22
+ "transformers_version": "5.0.0",
23
+ "use_cache": true
24
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 768,
12
+ "decoder_attention_heads": 12,
13
+ "decoder_ffn_dim": 3072,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 12,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 12,
20
+ "encoder_ffn_dim": 3072,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 12,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": null,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "mask_feature_length": 10,
28
+ "mask_feature_min_masks": 0,
29
+ "mask_feature_prob": 0.0,
30
+ "mask_time_length": 10,
31
+ "mask_time_min_masks": 2,
32
+ "mask_time_prob": 0.05,
33
+ "max_source_positions": 1500,
34
+ "max_target_positions": 448,
35
+ "median_filter_width": 7,
36
+ "model_type": "whisper",
37
+ "num_hidden_layers": 12,
38
+ "num_mel_bins": 80,
39
+ "pad_token_id": 50257,
40
+ "scale_embedding": false,
41
+ "suppress_tokens": null,
42
+ "tie_word_embeddings": true,
43
+ "transformers_version": "5.0.0",
44
+ "use_cache": false,
45
+ "use_weighted_layer_sum": false,
46
+ "vocab_size": 51865
47
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50257,
4
+ "decoder_start_token_id": 50258,
5
+ "eos_token_id": 50257,
6
+ "forced_decoder_ids": [
7
+ [
8
+ 1,
9
+ 50284
10
+ ],
11
+ [
12
+ 2,
13
+ 50359
14
+ ],
15
+ [
16
+ 3,
17
+ 50363
18
+ ]
19
+ ],
20
+ "pad_token_id": 50257,
21
+ "suppress_tokens": [],
22
+ "transformers_version": "5.0.0",
23
+ "use_cache": true
24
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5417baa00c9009a74e7a3f17575014a3cc3a1e43f3407997ecd80b3e8f2ac4e8
3
+ size 966995080
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992a50903a0add28374ab42f1814cbc0b14f78d5c22927f193ca724f9db01456
3
+ size 1934288064
last-checkpoint/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e9dc2a87fb3b392d6b9b7932857c6817592c8fdc38049cbbe310a8d79fb309
3
+ size 14645
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd8939a8c02d48e77c9db512ab2594fc61d70c3696d1cc22fe125efc6192af2b
3
+ size 1383
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7f06053cf6e98103a6c6505543495fe3d474861072e71c165b5a31c7258103
3
+ size 1465
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,524 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3501,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.042854081851296334,
14
+ "grad_norm": 23.36131477355957,
15
+ "learning_rate": 4.9000000000000005e-06,
16
+ "loss": 3.8926907348632813,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.08570816370259267,
21
+ "grad_norm": 18.458728790283203,
22
+ "learning_rate": 9.9e-06,
23
+ "loss": 2.958443298339844,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.128562245553889,
28
+ "grad_norm": 17.175376892089844,
29
+ "learning_rate": 9.855924728021171e-06,
30
+ "loss": 2.4218824768066405,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.17141632740518534,
35
+ "grad_norm": 15.591636657714844,
36
+ "learning_rate": 9.708909144369304e-06,
37
+ "loss": 2.371946258544922,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.2142704092564817,
42
+ "grad_norm": 14.409390449523926,
43
+ "learning_rate": 9.561893560717437e-06,
44
+ "loss": 2.087607421875,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.257124491107778,
49
+ "grad_norm": 13.630759239196777,
50
+ "learning_rate": 9.41487797706557e-06,
51
+ "loss": 2.0599404907226564,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.2999785729590744,
56
+ "grad_norm": 11.94897747039795,
57
+ "learning_rate": 9.267862393413703e-06,
58
+ "loss": 2.0533935546875,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.3428326548103707,
63
+ "grad_norm": 13.442337989807129,
64
+ "learning_rate": 9.120846809761836e-06,
65
+ "loss": 1.9987808227539063,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.38568673666166703,
70
+ "grad_norm": 15.808327674865723,
71
+ "learning_rate": 8.973831226109969e-06,
72
+ "loss": 1.937767791748047,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.4285408185129634,
77
+ "grad_norm": 15.030048370361328,
78
+ "learning_rate": 8.826815642458101e-06,
79
+ "loss": 1.889931640625,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.4713949003642597,
84
+ "grad_norm": 12.118426322937012,
85
+ "learning_rate": 8.679800058806234e-06,
86
+ "loss": 1.7828077697753906,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.514248982215556,
91
+ "grad_norm": 12.384000778198242,
92
+ "learning_rate": 8.532784475154367e-06,
93
+ "loss": 1.8068829345703126,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.5571030640668524,
98
+ "grad_norm": 10.589759826660156,
99
+ "learning_rate": 8.3857688915025e-06,
100
+ "loss": 1.8311549377441407,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.5999571459181487,
105
+ "grad_norm": 13.395003318786621,
106
+ "learning_rate": 8.238753307850633e-06,
107
+ "loss": 1.7994259643554686,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.642811227769445,
112
+ "grad_norm": 13.279837608337402,
113
+ "learning_rate": 8.091737724198766e-06,
114
+ "loss": 1.6858552551269532,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.6856653096207413,
119
+ "grad_norm": 12.410480499267578,
120
+ "learning_rate": 7.944722140546898e-06,
121
+ "loss": 1.7533489990234374,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.7285193914720377,
126
+ "grad_norm": 10.59311294555664,
127
+ "learning_rate": 7.797706556895031e-06,
128
+ "loss": 1.6539369201660157,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.7713734733233341,
133
+ "grad_norm": 12.877548217773438,
134
+ "learning_rate": 7.650690973243164e-06,
135
+ "loss": 1.6823117065429687,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.8142275551746304,
140
+ "grad_norm": 12.337571144104004,
141
+ "learning_rate": 7.503675389591297e-06,
142
+ "loss": 1.6649679565429687,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.8570816370259268,
147
+ "grad_norm": 12.265089988708496,
148
+ "learning_rate": 7.35665980593943e-06,
149
+ "loss": 1.643274688720703,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.899935718877223,
154
+ "grad_norm": 13.716150283813477,
155
+ "learning_rate": 7.209644222287563e-06,
156
+ "loss": 1.6112545776367186,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.9427898007285194,
161
+ "grad_norm": 13.659560203552246,
162
+ "learning_rate": 7.0626286386356955e-06,
163
+ "loss": 1.6950546264648438,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.9856438825798157,
168
+ "grad_norm": 10.260647773742676,
169
+ "learning_rate": 6.915613054983828e-06,
170
+ "loss": 1.640511474609375,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 1.0282836940218556,
175
+ "grad_norm": 10.752132415771484,
176
+ "learning_rate": 6.768597471331961e-06,
177
+ "loss": 1.4724107360839844,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 1.071137775873152,
182
+ "grad_norm": 12.311515808105469,
183
+ "learning_rate": 6.621581887680094e-06,
184
+ "loss": 1.5025825500488281,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 1.1139918577244483,
189
+ "grad_norm": 11.75078010559082,
190
+ "learning_rate": 6.474566304028228e-06,
191
+ "loss": 1.4357522583007813,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 1.1568459395757447,
196
+ "grad_norm": 11.204419136047363,
197
+ "learning_rate": 6.327550720376361e-06,
198
+ "loss": 1.5433657836914063,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 1.199700021427041,
203
+ "grad_norm": 9.38224983215332,
204
+ "learning_rate": 6.1805351367244935e-06,
205
+ "loss": 1.4390789794921874,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 1.2425541032783372,
210
+ "grad_norm": 12.256275177001953,
211
+ "learning_rate": 6.033519553072626e-06,
212
+ "loss": 1.3136796569824218,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 1.2854081851296337,
217
+ "grad_norm": 8.440166473388672,
218
+ "learning_rate": 5.886503969420759e-06,
219
+ "loss": 1.4067805480957032,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 1.3282622669809299,
224
+ "grad_norm": 10.991435050964355,
225
+ "learning_rate": 5.739488385768892e-06,
226
+ "loss": 1.4254563903808595,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 1.3711163488322262,
231
+ "grad_norm": 11.518052101135254,
232
+ "learning_rate": 5.592472802117025e-06,
233
+ "loss": 1.447697296142578,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 1.4139704306835226,
238
+ "grad_norm": 12.232306480407715,
239
+ "learning_rate": 5.445457218465158e-06,
240
+ "loss": 1.370250244140625,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 1.456824512534819,
245
+ "grad_norm": 18.690576553344727,
246
+ "learning_rate": 5.2984416348132905e-06,
247
+ "loss": 1.327724151611328,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 1.4996785943861153,
252
+ "grad_norm": 10.078082084655762,
253
+ "learning_rate": 5.151426051161423e-06,
254
+ "loss": 1.3785079956054687,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 1.5425326762374116,
259
+ "grad_norm": 10.285982131958008,
260
+ "learning_rate": 5.004410467509556e-06,
261
+ "loss": 1.3937582397460937,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 1.585386758088708,
266
+ "grad_norm": 12.025802612304688,
267
+ "learning_rate": 4.85739488385769e-06,
268
+ "loss": 1.308221893310547,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 1.6282408399400041,
273
+ "grad_norm": 11.093772888183594,
274
+ "learning_rate": 4.710379300205822e-06,
275
+ "loss": 1.361168212890625,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 1.6710949217913007,
280
+ "grad_norm": 12.764751434326172,
281
+ "learning_rate": 4.563363716553955e-06,
282
+ "loss": 1.4194657897949219,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 1.7139490036425968,
287
+ "grad_norm": 15.253408432006836,
288
+ "learning_rate": 4.416348132902088e-06,
289
+ "loss": 1.3775755310058593,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 1.7568030854938934,
294
+ "grad_norm": 13.753087043762207,
295
+ "learning_rate": 4.2693325492502205e-06,
296
+ "loss": 1.392965087890625,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 1.7996571673451895,
301
+ "grad_norm": 10.085309982299805,
302
+ "learning_rate": 4.122316965598353e-06,
303
+ "loss": 1.3251914978027344,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 1.8425112491964861,
308
+ "grad_norm": 12.176279067993164,
309
+ "learning_rate": 3.975301381946486e-06,
310
+ "loss": 1.3795436096191407,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 1.8853653310477823,
315
+ "grad_norm": 11.271302223205566,
316
+ "learning_rate": 3.82828579829462e-06,
317
+ "loss": 1.4280400085449219,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 1.9282194128990786,
322
+ "grad_norm": 13.179277420043945,
323
+ "learning_rate": 3.6812702146427527e-06,
324
+ "loss": 1.288242645263672,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 1.971073494750375,
329
+ "grad_norm": 11.995197296142578,
330
+ "learning_rate": 3.5342546309908856e-06,
331
+ "loss": 1.338401336669922,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 2.0137133061924146,
336
+ "grad_norm": 12.60085391998291,
337
+ "learning_rate": 3.3872390473390184e-06,
338
+ "loss": 1.2804518127441407,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 2.056567388043711,
343
+ "grad_norm": 13.999833106994629,
344
+ "learning_rate": 3.240223463687151e-06,
345
+ "loss": 1.2467501831054688,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 2.0994214698950073,
350
+ "grad_norm": 14.353278160095215,
351
+ "learning_rate": 3.0932078800352837e-06,
352
+ "loss": 1.216924819946289,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 2.142275551746304,
357
+ "grad_norm": 15.039190292358398,
358
+ "learning_rate": 2.9461922963834165e-06,
359
+ "loss": 1.1382264709472656,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 2.1851296335976,
364
+ "grad_norm": 11.174071311950684,
365
+ "learning_rate": 2.79917671273155e-06,
366
+ "loss": 1.2543386840820312,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 2.2279837154488966,
371
+ "grad_norm": 9.42978572845459,
372
+ "learning_rate": 2.6521611290796826e-06,
373
+ "loss": 1.2374308013916016,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 2.2708377973001928,
378
+ "grad_norm": 12.46211051940918,
379
+ "learning_rate": 2.5051455454278155e-06,
380
+ "loss": 1.2151295471191406,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 2.3136918791514893,
385
+ "grad_norm": 11.10874080657959,
386
+ "learning_rate": 2.3581299617759483e-06,
387
+ "loss": 1.2481879425048827,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 2.3565459610027855,
392
+ "grad_norm": 11.55053997039795,
393
+ "learning_rate": 2.211114378124081e-06,
394
+ "loss": 1.2572499847412109,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 2.399400042854082,
399
+ "grad_norm": 11.209309577941895,
400
+ "learning_rate": 2.0640987944722144e-06,
401
+ "loss": 1.2424217224121095,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 2.442254124705378,
406
+ "grad_norm": 11.722271919250488,
407
+ "learning_rate": 1.9170832108203473e-06,
408
+ "loss": 1.1698280334472657,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 2.4851082065566743,
413
+ "grad_norm": 9.327156066894531,
414
+ "learning_rate": 1.77006762716848e-06,
415
+ "loss": 1.230049591064453,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 2.527962288407971,
420
+ "grad_norm": 12.329734802246094,
421
+ "learning_rate": 1.6230520435166128e-06,
422
+ "loss": 1.2203353118896485,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 2.5708163702592675,
427
+ "grad_norm": 9.99496841430664,
428
+ "learning_rate": 1.4760364598647458e-06,
429
+ "loss": 1.220074462890625,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 2.6136704521105636,
434
+ "grad_norm": 12.380325317382812,
435
+ "learning_rate": 1.3290208762128787e-06,
436
+ "loss": 1.2719744873046874,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 2.6565245339618597,
441
+ "grad_norm": 9.495610237121582,
442
+ "learning_rate": 1.1820052925610115e-06,
443
+ "loss": 1.2103775024414063,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 2.6993786158131563,
448
+ "grad_norm": 10.106226921081543,
449
+ "learning_rate": 1.0349897089091444e-06,
450
+ "loss": 1.2538141632080078,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 2.7422326976644524,
455
+ "grad_norm": 10.874300956726074,
456
+ "learning_rate": 8.879741252572774e-07,
457
+ "loss": 1.2003070068359376,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 2.785086779515749,
462
+ "grad_norm": 12.79405689239502,
463
+ "learning_rate": 7.409585416054102e-07,
464
+ "loss": 1.2319601440429688,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 2.827940861367045,
469
+ "grad_norm": 11.287105560302734,
470
+ "learning_rate": 5.939429579535431e-07,
471
+ "loss": 1.2414318084716798,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 2.8707949432183417,
476
+ "grad_norm": 11.550670623779297,
477
+ "learning_rate": 4.46927374301676e-07,
478
+ "loss": 1.1638024139404297,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 2.913649025069638,
483
+ "grad_norm": 9.189581871032715,
484
+ "learning_rate": 2.999117906498089e-07,
485
+ "loss": 1.2275858306884766,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 2.956503106920934,
490
+ "grad_norm": 11.081841468811035,
491
+ "learning_rate": 1.528962069979418e-07,
492
+ "loss": 1.205632095336914,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 2.9993571887722306,
497
+ "grad_norm": 10.45347785949707,
498
+ "learning_rate": 5.880623346074684e-09,
499
+ "loss": 1.261582794189453,
500
+ "step": 3500
501
+ }
502
+ ],
503
+ "logging_steps": 50,
504
+ "max_steps": 3501,
505
+ "num_input_tokens_seen": 0,
506
+ "num_train_epochs": 3,
507
+ "save_steps": 500,
508
+ "stateful_callbacks": {
509
+ "TrainerControl": {
510
+ "args": {
511
+ "should_epoch_stop": false,
512
+ "should_evaluate": false,
513
+ "should_log": false,
514
+ "should_save": true,
515
+ "should_training_stop": true
516
+ },
517
+ "attributes": {}
518
+ }
519
+ },
520
+ "total_flos": 3.232214200664064e+19,
521
+ "train_batch_size": 8,
522
+ "trial_name": null,
523
+ "trial_params": null
524
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b18690c36a2ba60be0169fdb2b49bb8d71f62fadd440edab41999d978e8916e
3
+ size 5393
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5417baa00c9009a74e7a3f17575014a3cc3a1e43f3407997ecd80b3e8f2ac4e8
3
+ size 966995080
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
processor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "chunk_length": 30,
4
+ "dither": 0.0,
5
+ "feature_extractor_type": "WhisperFeatureExtractor",
6
+ "feature_size": 80,
7
+ "hop_length": 160,
8
+ "n_fft": 400,
9
+ "n_samples": 480000,
10
+ "nb_max_frames": 3000,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "return_attention_mask": false,
14
+ "sampling_rate": 16000
15
+ },
16
+ "processor_class": "WhisperProcessor"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|endoftext|>",
10
+ "<|startoftranscript|>",
11
+ "<|en|>",
12
+ "<|zh|>",
13
+ "<|de|>",
14
+ "<|es|>",
15
+ "<|ru|>",
16
+ "<|ko|>",
17
+ "<|fr|>",
18
+ "<|ja|>",
19
+ "<|pt|>",
20
+ "<|tr|>",
21
+ "<|pl|>",
22
+ "<|ca|>",
23
+ "<|nl|>",
24
+ "<|ar|>",
25
+ "<|sv|>",
26
+ "<|it|>",
27
+ "<|id|>",
28
+ "<|hi|>",
29
+ "<|fi|>",
30
+ "<|vi|>",
31
+ "<|he|>",
32
+ "<|uk|>",
33
+ "<|el|>",
34
+ "<|ms|>",
35
+ "<|cs|>",
36
+ "<|ro|>",
37
+ "<|da|>",
38
+ "<|hu|>",
39
+ "<|ta|>",
40
+ "<|no|>",
41
+ "<|th|>",
42
+ "<|ur|>",
43
+ "<|hr|>",
44
+ "<|bg|>",
45
+ "<|lt|>",
46
+ "<|la|>",
47
+ "<|mi|>",
48
+ "<|ml|>",
49
+ "<|cy|>",
50
+ "<|sk|>",
51
+ "<|te|>",
52
+ "<|fa|>",
53
+ "<|lv|>",
54
+ "<|bn|>",
55
+ "<|sr|>",
56
+ "<|az|>",
57
+ "<|sl|>",
58
+ "<|kn|>",
59
+ "<|et|>",
60
+ "<|mk|>",
61
+ "<|br|>",
62
+ "<|eu|>",
63
+ "<|is|>",
64
+ "<|hy|>",
65
+ "<|ne|>",
66
+ "<|mn|>",
67
+ "<|bs|>",
68
+ "<|kk|>",
69
+ "<|sq|>",
70
+ "<|sw|>",
71
+ "<|gl|>",
72
+ "<|mr|>",
73
+ "<|pa|>",
74
+ "<|si|>",
75
+ "<|km|>",
76
+ "<|sn|>",
77
+ "<|yo|>",
78
+ "<|so|>",
79
+ "<|af|>",
80
+ "<|oc|>",
81
+ "<|ka|>",
82
+ "<|be|>",
83
+ "<|tg|>",
84
+ "<|sd|>",
85
+ "<|gu|>",
86
+ "<|am|>",
87
+ "<|yi|>",
88
+ "<|lo|>",
89
+ "<|uz|>",
90
+ "<|fo|>",
91
+ "<|ht|>",
92
+ "<|ps|>",
93
+ "<|tk|>",
94
+ "<|nn|>",
95
+ "<|mt|>",
96
+ "<|sa|>",
97
+ "<|lb|>",
98
+ "<|my|>",
99
+ "<|bo|>",
100
+ "<|tl|>",
101
+ "<|mg|>",
102
+ "<|as|>",
103
+ "<|tt|>",
104
+ "<|haw|>",
105
+ "<|ln|>",
106
+ "<|ha|>",
107
+ "<|ba|>",
108
+ "<|jw|>",
109
+ "<|su|>",
110
+ "<|translate|>",
111
+ "<|transcribe|>",
112
+ "<|startoflm|>",
113
+ "<|startofprev|>",
114
+ "<|nocaptions|>",
115
+ "<|notimestamps|>"
116
+ ],
117
+ "is_local": false,
118
+ "language": null,
119
+ "model_max_length": 1024,
120
+ "model_specific_special_tokens": {},
121
+ "pad_token": "<|endoftext|>",
122
+ "predict_timestamps": false,
123
+ "processor_class": "WhisperProcessor",
124
+ "return_attention_mask": false,
125
+ "task": null,
126
+ "tokenizer_class": "WhisperTokenizer",
127
+ "unk_token": "<|endoftext|>"
128
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b18690c36a2ba60be0169fdb2b49bb8d71f62fadd440edab41999d978e8916e
3
+ size 5393