Hugging Face's logo

nomnoos37
/
stt-turbo-1227-v1.1-peft-eng-1k

PEFT
TensorBoard
Safetensors
Korean
Generated from Trainer
Model card Files Metrics Community
nomnoos37 commited on
Commit
eccb8af
·
verified ·
1 Parent(s): 12a4db8

nomnoos37/stt-turbo-1226-v1.4

Browse files
Files changed (6) hide show
  1. README.md +162 -0
  2. adapter_config.json +35 -0
  3. adapter_model.safetensors +3 -0
  4. preprocessor_config.json +14 -0
  5. runs/Dec27_03-59-10_gglabs-a6000/events.out.tfevents.1735289950.gglabs-a6000 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ language:
4
+ - ko
5
+ license: mit
6
+ base_model: openai/whisper-large-v3-turbo
7
+ tags:
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Whisper Small ko
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Whisper Small ko
18
+
19
+ This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the custom dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.3628
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 3e-05
41
+ - train_batch_size: 64
42
+ - eval_batch_size: 256
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 100
47
+ - training_steps: 1000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.9038 | 0.0813 | 10 | 1.5912 |
55
+ | 0.9253 | 0.1626 | 20 | 1.5826 |
56
+ | 0.8846 | 0.2439 | 30 | 1.5672 |
57
+ | 0.8716 | 0.3252 | 40 | 1.5414 |
58
+ | 0.8208 | 0.4065 | 50 | 1.4999 |
59
+ | 0.7729 | 0.4878 | 60 | 1.4312 |
60
+ | 0.6709 | 0.5691 | 70 | 1.3037 |
61
+ | 0.4743 | 0.6504 | 80 | 1.0660 |
62
+ | 0.3255 | 0.7317 | 90 | 0.9261 |
63
+ | 0.2445 | 0.8130 | 100 | 0.8726 |
64
+ | 0.2058 | 0.8943 | 110 | 0.8373 |
65
+ | 0.1868 | 0.9756 | 120 | 0.8078 |
66
+ | 0.1693 | 1.0569 | 130 | 0.7770 |
67
+ | 0.149 | 1.1382 | 140 | 0.7423 |
68
+ | 0.1342 | 1.2195 | 150 | 0.7108 |
69
+ | 0.1379 | 1.3008 | 160 | 0.6793 |
70
+ | 0.1062 | 1.3821 | 170 | 0.6545 |
71
+ | 0.1105 | 1.4634 | 180 | 0.6406 |
72
+ | 0.0938 | 1.5447 | 190 | 0.6334 |
73
+ | 0.1214 | 1.6260 | 200 | 0.6210 |
74
+ | 0.0894 | 1.7073 | 210 | 0.6023 |
75
+ | 0.0806 | 1.7886 | 220 | 0.5867 |
76
+ | 0.0705 | 1.8699 | 230 | 0.5730 |
77
+ | 0.0768 | 1.9512 | 240 | 0.5677 |
78
+ | 0.0671 | 2.0325 | 250 | 0.5617 |
79
+ | 0.0782 | 2.1138 | 260 | 0.5549 |
80
+ | 0.0919 | 2.1951 | 270 | 0.5433 |
81
+ | 0.0689 | 2.2764 | 280 | 0.5278 |
82
+ | 0.0763 | 2.3577 | 290 | 0.5220 |
83
+ | 0.0651 | 2.4390 | 300 | 0.5192 |
84
+ | 0.0601 | 2.5203 | 310 | 0.5108 |
85
+ | 0.0638 | 2.6016 | 320 | 0.5039 |
86
+ | 0.0596 | 2.6829 | 330 | 0.4954 |
87
+ | 0.0635 | 2.7642 | 340 | 0.4901 |
88
+ | 0.0604 | 2.8455 | 350 | 0.4882 |
89
+ | 0.0473 | 2.9268 | 360 | 0.4868 |
90
+ | 0.0601 | 3.0081 | 370 | 0.4845 |
91
+ | 0.0513 | 3.0894 | 380 | 0.4780 |
92
+ | 0.0608 | 3.1707 | 390 | 0.4723 |
93
+ | 0.0593 | 3.2520 | 400 | 0.4678 |
94
+ | 0.0508 | 3.3333 | 410 | 0.4644 |
95
+ | 0.0476 | 3.4146 | 420 | 0.4605 |
96
+ | 0.0629 | 3.4959 | 430 | 0.4584 |
97
+ | 0.0467 | 3.5772 | 440 | 0.4551 |
98
+ | 0.0718 | 3.6585 | 450 | 0.4462 |
99
+ | 0.0496 | 3.7398 | 460 | 0.4392 |
100
+ | 0.0477 | 3.8211 | 470 | 0.4371 |
101
+ | 0.0461 | 3.9024 | 480 | 0.4348 |
102
+ | 0.0464 | 3.9837 | 490 | 0.4320 |
103
+ | 0.0571 | 4.0650 | 500 | 0.4299 |
104
+ | 0.0446 | 4.1463 | 510 | 0.4271 |
105
+ | 0.0435 | 4.2276 | 520 | 0.4253 |
106
+ | 0.0461 | 4.3089 | 530 | 0.4242 |
107
+ | 0.0467 | 4.3902 | 540 | 0.4222 |
108
+ | 0.0499 | 4.4715 | 550 | 0.4200 |
109
+ | 0.0607 | 4.5528 | 560 | 0.4162 |
110
+ | 0.0435 | 4.6341 | 570 | 0.4097 |
111
+ | 0.0463 | 4.7154 | 580 | 0.4047 |
112
+ | 0.0382 | 4.7967 | 590 | 0.4021 |
113
+ | 0.0452 | 4.8780 | 600 | 0.4013 |
114
+ | 0.0447 | 4.9593 | 610 | 0.4007 |
115
+ | 0.0478 | 5.0407 | 620 | 0.3992 |
116
+ | 0.0411 | 5.1220 | 630 | 0.3983 |
117
+ | 0.0429 | 5.2033 | 640 | 0.3959 |
118
+ | 0.0384 | 5.2846 | 650 | 0.3959 |
119
+ | 0.0377 | 5.3659 | 660 | 0.3944 |
120
+ | 0.0443 | 5.4472 | 670 | 0.3907 |
121
+ | 0.0366 | 5.5285 | 680 | 0.3893 |
122
+ | 0.0413 | 5.6098 | 690 | 0.3883 |
123
+ | 0.0439 | 5.6911 | 700 | 0.3877 |
124
+ | 0.0441 | 5.7724 | 710 | 0.3868 |
125
+ | 0.0371 | 5.8537 | 720 | 0.3851 |
126
+ | 0.0461 | 5.9350 | 730 | 0.3837 |
127
+ | 0.0619 | 6.0163 | 740 | 0.3797 |
128
+ | 0.0393 | 6.0976 | 750 | 0.3781 |
129
+ | 0.0391 | 6.1789 | 760 | 0.3767 |
130
+ | 0.0383 | 6.2602 | 770 | 0.3746 |
131
+ | 0.041 | 6.3415 | 780 | 0.3731 |
132
+ | 0.0359 | 6.4228 | 790 | 0.3716 |
133
+ | 0.0448 | 6.5041 | 800 | 0.3709 |
134
+ | 0.0379 | 6.5854 | 810 | 0.3697 |
135
+ | 0.0434 | 6.6667 | 820 | 0.3693 |
136
+ | 0.0503 | 6.7480 | 830 | 0.3688 |
137
+ | 0.04 | 6.8293 | 840 | 0.3684 |
138
+ | 0.0378 | 6.9106 | 850 | 0.3682 |
139
+ | 0.0441 | 6.9919 | 860 | 0.3675 |
140
+ | 0.0344 | 7.0732 | 870 | 0.3669 |
141
+ | 0.0401 | 7.1545 | 880 | 0.3662 |
142
+ | 0.0516 | 7.2358 | 890 | 0.3654 |
143
+ | 0.0309 | 7.3171 | 900 | 0.3654 |
144
+ | 0.0314 | 7.3984 | 910 | 0.3653 |
145
+ | 0.0403 | 7.4797 | 920 | 0.3650 |
146
+ | 0.0459 | 7.5610 | 930 | 0.3646 |
147
+ | 0.0299 | 7.6423 | 940 | 0.3642 |
148
+ | 0.0337 | 7.7236 | 950 | 0.3638 |
149
+ | 0.0352 | 7.8049 | 960 | 0.3636 |
150
+ | 0.0598 | 7.8862 | 970 | 0.3635 |
151
+ | 0.0421 | 7.9675 | 980 | 0.3630 |
152
+ | 0.0409 | 8.0488 | 990 | 0.3628 |
153
+ | 0.0369 | 8.1301 | 1000 | 0.3628 |
154
+
155
+
156
+ ### Framework versions
157
+
158
+ - PEFT 0.14.0
159
+ - Transformers 4.47.1
160
+ - Pytorch 2.5.1+cu124
161
+ - Datasets 3.2.0
162
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "WhisperForConditionalGeneration",
5
+ "parent_library": "transformers.models.whisper.modeling_whisper"
6
+ },
7
+ "base_model_name_or_path": "openai/whisper-large-v3-turbo",
8
+ "bias": "none",
9
+ "eva_config": null,
10
+ "exclude_modules": null,
11
+ "fan_in_fan_out": false,
12
+ "inference_mode": true,
13
+ "init_lora_weights": true,
14
+ "layer_replication": null,
15
+ "layers_pattern": null,
16
+ "layers_to_transform": null,
17
+ "loftq_config": {},
18
+ "lora_alpha": 64,
19
+ "lora_bias": false,
20
+ "lora_dropout": 0.05,
21
+ "megatron_config": null,
22
+ "megatron_core": "megatron.core",
23
+ "modules_to_save": null,
24
+ "peft_type": "LORA",
25
+ "r": 32,
26
+ "rank_pattern": {},
27
+ "revision": null,
28
+ "target_modules": [
29
+ "v_proj",
30
+ "q_proj"
31
+ ],
32
+ "task_type": null,
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9d0f073e582a584d5983646f92c7e86d3354389ca986a6e3dfce836255381f
3
+ size 26237160
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
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
+ }
runs/Dec27_03-59-10_gglabs-a6000/events.out.tfevents.1735289950.gglabs-a6000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6d710ce24a043add579acb3042878e596700be2c0f1272d39aa719561ca621
3
+ size 54775
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8bc2bf0d38bc90af46fcd0f849f7482bc783c1e3c2774e0037164bef58e8b7
3
+ size 5496