Hugging Face's logo

gary109
/
ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
gary109/AI_Light_Dance
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
gary109 commited on
Commit
0b3cc23
•
1 Parent(s): 5e5ca5c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +59 -63
README.md CHANGED
@@ -1,8 +1,6 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - automatic-speech-recognition
5
- - gary109/AI_Light_Dance
6
  - generated_from_trainer
7
  model-index:
8
  - name: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
@@ -14,10 +12,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
16
 
17
- This model is a fine-tuned version of [gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1](https://huggingface.co/gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1) on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING3 dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5352
20
- - Wer: 0.2490
21
 
22
  ## Model description
23
 
@@ -36,72 +34,70 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 2e-06
40
- - train_batch_size: 8
41
- - eval_batch_size: 8
42
  - seed: 42
43
- - gradient_accumulation_steps: 8
44
- - total_train_batch_size: 64
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - lr_scheduler_warmup_steps: 50
48
  - num_epochs: 50.0
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 0.3818 | 1.0 | 72 | 0.5569 | 0.2535 |
56
- | 0.3686 | 2.0 | 144 | 0.5535 | 0.2501 |
57
- | 0.3562 | 3.0 | 216 | 0.5526 | 0.2501 |
58
- | 0.3506 | 4.0 | 288 | 0.5460 | 0.2520 |
59
- | 0.369 | 5.0 | 360 | 0.5390 | 0.2484 |
60
- | 0.3683 | 6.0 | 432 | 0.5426 | 0.2474 |
61
- | 0.3541 | 7.0 | 504 | 0.5452 | 0.2495 |
62
- | 0.369 | 8.0 | 576 | 0.5468 | 0.2490 |
63
- | 0.358 | 9.0 | 648 | 0.5471 | 0.2453 |
64
- | 0.3765 | 10.0 | 720 | 0.5376 | 0.2459 |
65
- | 0.3654 | 11.0 | 792 | 0.5407 | 0.2486 |
66
- | 0.373 | 12.0 | 864 | 0.5390 | 0.2475 |
67
- | 0.3606 | 13.0 | 936 | 0.5441 | 0.2472 |
68
- | 0.369 | 14.0 | 1008 | 0.5388 | 0.2490 |
69
- | 0.3762 | 15.0 | 1080 | 0.5389 | 0.2497 |
70
- | 0.3821 | 16.0 | 1152 | 0.5352 | 0.2490 |
71
- | 0.3605 | 17.0 | 1224 | 0.5434 | 0.2492 |
72
- | 0.3703 | 18.0 | 1296 | 0.5415 | 0.2500 |
73
- | 0.3667 | 19.0 | 1368 | 0.5499 | 0.2487 |
74
- | 0.3703 | 20.0 | 1440 | 0.5482 | 0.2494 |
75
- | 0.369 | 21.0 | 1512 | 0.5418 | 0.2504 |
76
- | 0.3708 | 22.0 | 1584 | 0.5437 | 0.2479 |
77
- | 0.3609 | 23.0 | 1656 | 0.5453 | 0.2480 |
78
- | 0.3534 | 24.0 | 1728 | 0.5393 | 0.2484 |
79
- | 0.3656 | 25.0 | 1800 | 0.5363 | 0.2477 |
80
- | 0.3713 | 26.0 | 1872 | 0.5406 | 0.2461 |
81
- | 0.3572 | 27.0 | 1944 | 0.5369 | 0.2465 |
82
- | 0.3665 | 28.0 | 2016 | 0.5375 | 0.2466 |
83
- | 0.3748 | 29.0 | 2088 | 0.5367 | 0.2480 |
84
- | 0.3769 | 30.0 | 2160 | 0.5359 | 0.2459 |
85
- | 0.3634 | 31.0 | 2232 | 0.5417 | 0.2471 |
86
- | 0.3627 | 32.0 | 2304 | 0.5398 | 0.2473 |
87
- | 0.3497 | 33.0 | 2376 | 0.5428 | 0.2483 |
88
- | 0.3479 | 34.0 | 2448 | 0.5390 | 0.2481 |
89
- | 0.363 | 35.0 | 2520 | 0.5388 | 0.2478 |
90
- | 0.3622 | 36.0 | 2592 | 0.5396 | 0.2490 |
91
- | 0.3685 | 37.0 | 2664 | 0.5408 | 0.2479 |
92
- | 0.356 | 38.0 | 2736 | 0.5385 | 0.2459 |
93
- | 0.3529 | 39.0 | 2808 | 0.5389 | 0.2467 |
94
- | 0.3702 | 40.0 | 2880 | 0.5392 | 0.2482 |
95
- | 0.3645 | 41.0 | 2952 | 0.5408 | 0.2467 |
96
- | 0.3489 | 42.0 | 3024 | 0.5406 | 0.2474 |
97
- | 0.3556 | 43.0 | 3096 | 0.5402 | 0.2472 |
98
- | 0.356 | 44.0 | 3168 | 0.5386 | 0.2468 |
99
- | 0.3632 | 45.0 | 3240 | 0.5402 | 0.2463 |
100
- | 0.3693 | 46.0 | 3312 | 0.5401 | 0.2472 |
101
- | 0.3593 | 47.0 | 3384 | 0.5390 | 0.2463 |
102
- | 0.3515 | 48.0 | 3456 | 0.5399 | 0.2468 |
103
- | 0.3485 | 49.0 | 3528 | 0.5392 | 0.2461 |
104
- | 0.3591 | 50.0 | 3600 | 0.5403 | 0.2461 |
105
 
106
 
107
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
  tags:
 
 
4
  - generated_from_trainer
5
  model-index:
6
  - name: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
 
12
 
13
  # ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
14
 
15
+ This model is a fine-tuned version of [gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1](https://huggingface.co/gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.5709
18
+ - Wer: 0.2379
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 1e-06
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 2
40
  - seed: 42
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 1000
44
  - num_epochs: 50.0
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:------:|:---------------:|:------:|
51
+ | 0.3909 | 1.0 | 2309 | 0.5615 | 0.2459 |
52
+ | 0.4094 | 2.0 | 4618 | 0.5654 | 0.2439 |
53
+ | 0.326 | 3.0 | 6927 | 0.5568 | 0.2470 |
54
+ | 0.4577 | 4.0 | 9236 | 0.5795 | 0.2474 |
55
+ | 0.3628 | 5.0 | 11545 | 0.5459 | 0.2463 |
56
+ | 0.3135 | 6.0 | 13854 | 0.5582 | 0.2473 |
57
+ | 0.5058 | 7.0 | 16163 | 0.5677 | 0.2439 |
58
+ | 0.3188 | 8.0 | 18472 | 0.5646 | 0.2445 |
59
+ | 0.3589 | 9.0 | 20781 | 0.5626 | 0.2479 |
60
+ | 0.4021 | 10.0 | 23090 | 0.5722 | 0.2452 |
61
+ | 0.4362 | 11.0 | 25399 | 0.5659 | 0.2431 |
62
+ | 0.3215 | 12.0 | 27708 | 0.5658 | 0.2445 |
63
+ | 0.3646 | 13.0 | 30017 | 0.5785 | 0.2459 |
64
+ | 0.3757 | 14.0 | 32326 | 0.5757 | 0.2418 |
65
+ | 0.3311 | 15.0 | 34635 | 0.5672 | 0.2455 |
66
+ | 0.3709 | 16.0 | 36944 | 0.5669 | 0.2434 |
67
+ | 0.3342 | 17.0 | 39253 | 0.5610 | 0.2455 |
68
+ | 0.3236 | 18.0 | 41562 | 0.5652 | 0.2436 |
69
+ | 0.3566 | 19.0 | 43871 | 0.5773 | 0.2407 |
70
+ | 0.2912 | 20.0 | 46180 | 0.5764 | 0.2453 |
71
+ | 0.3652 | 21.0 | 48489 | 0.5732 | 0.2423 |
72
+ | 0.3785 | 22.0 | 50798 | 0.5696 | 0.2423 |
73
+ | 0.3968 | 23.0 | 53107 | 0.5690 | 0.2429 |
74
+ | 0.2968 | 24.0 | 55416 | 0.5800 | 0.2427 |
75
+ | 0.428 | 25.0 | 57725 | 0.5704 | 0.2441 |
76
+ | 0.383 | 26.0 | 60034 | 0.5739 | 0.2450 |
77
+ | 0.3694 | 27.0 | 62343 | 0.5791 | 0.2437 |
78
+ | 0.3449 | 28.0 | 64652 | 0.5780 | 0.2451 |
79
+ | 0.3008 | 29.0 | 66961 | 0.5749 | 0.2418 |
80
+ | 0.3939 | 30.0 | 69270 | 0.5737 | 0.2424 |
81
+ | 0.3451 | 31.0 | 71579 | 0.5805 | 0.2402 |
82
+ | 0.3513 | 32.0 | 73888 | 0.5670 | 0.2379 |
83
+ | 0.3866 | 33.0 | 76197 | 0.5706 | 0.2389 |
84
+ | 0.3831 | 34.0 | 78506 | 0.5635 | 0.2401 |
85
+ | 0.3641 | 35.0 | 80815 | 0.5708 | 0.2405 |
86
+ | 0.3345 | 36.0 | 83124 | 0.5699 | 0.2405 |
87
+ | 0.2902 | 37.0 | 85433 | 0.5711 | 0.2373 |
88
+ | 0.2868 | 38.0 | 87742 | 0.5713 | 0.2389 |
89
+ | 0.3232 | 39.0 | 90051 | 0.5702 | 0.2392 |
90
+ | 0.3277 | 40.0 | 92360 | 0.5658 | 0.2393 |
91
+ | 0.3234 | 41.0 | 94669 | 0.5732 | 0.2412 |
92
+ | 0.3625 | 42.0 | 96978 | 0.5740 | 0.2396 |
93
+ | 0.4075 | 43.0 | 99287 | 0.5733 | 0.2389 |
94
+ | 0.3473 | 44.0 | 101596 | 0.5735 | 0.2394 |
95
+ | 0.3157 | 45.0 | 103905 | 0.5721 | 0.2391 |
96
+ | 0.3866 | 46.0 | 106214 | 0.5715 | 0.2381 |
97
+ | 0.4062 | 47.0 | 108523 | 0.5711 | 0.2380 |
98
+ | 0.3871 | 48.0 | 110832 | 0.5716 | 0.2380 |
99
+ | 0.2924 | 49.0 | 113141 | 0.5723 | 0.2374 |
100
+ | 0.3655 | 50.0 | 115450 | 0.5709 | 0.2379 |
101
 
102
 
103
  ### Framework versions