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
b4ae20a
•
1 Parent(s): 318a719

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +59 -61
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: 0.5577
20
- - Wer: 0.2682
21
 
22
  ## Model description
23
 
@@ -36,15 +34,15 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 8e-06
40
- - train_batch_size: 4
41
- - eval_batch_size: 4
42
  - seed: 42
43
- - gradient_accumulation_steps: 4
44
- - total_train_batch_size: 16
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - lr_scheduler_warmup_steps: 5000
48
  - num_epochs: 50.0
49
  - mixed_precision_training: Native AMP
50
 
@@ -52,56 +50,56 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
55
- | 0.4853 | 1.0 | 288 | 0.5760 | 0.3098 |
56
- | 0.48 | 2.0 | 576 | 0.5787 | 0.3085 |
57
- | 0.4625 | 3.0 | 864 | 0.5925 | 0.3112 |
58
- | 0.4704 | 4.0 | 1152 | 0.6065 | 0.3108 |
59
- | 0.4854 | 5.0 | 1440 | 0.6036 | 0.3112 |
60
- | 0.4918 | 6.0 | 1728 | 0.6007 | 0.3148 |
61
- | 0.4549 | 7.0 | 2016 | 0.6039 | 0.3073 |
62
- | 0.4546 | 8.0 | 2304 | 0.6129 | 0.3073 |
63
- | 0.4404 | 9.0 | 2592 | 0.6062 | 0.3054 |
64
- | 0.4681 | 10.0 | 2880 | 0.6063 | 0.3075 |
65
- | 0.469 | 11.0 | 3168 | 0.5881 | 0.3031 |
66
- | 0.4903 | 12.0 | 3456 | 0.5913 | 0.3047 |
67
- | 0.4677 | 13.0 | 3744 | 0.5921 | 0.3055 |
68
- | 0.502 | 14.0 | 4032 | 0.5905 | 0.3042 |
69
- | 0.5028 | 15.0 | 4320 | 0.5989 | 0.3088 |
70
- | 0.4706 | 16.0 | 4608 | 0.5665 | 0.3066 |
71
- | 0.4839 | 17.0 | 4896 | 0.6003 | 0.3111 |
72
- | 0.4733 | 18.0 | 5184 | 0.5937 | 0.3039 |
73
- | 0.4544 | 19.0 | 5472 | 0.5903 | 0.3025 |
74
- | 0.4616 | 20.0 | 5760 | 0.6064 | 0.2968 |
75
- | 0.475 | 21.0 | 6048 | 0.5883 | 0.2960 |
76
- | 0.4707 | 22.0 | 6336 | 0.5900 | 0.2888 |
77
- | 0.4562 | 23.0 | 6624 | 0.5642 | 0.2956 |
78
- | 0.455 | 24.0 | 6912 | 0.5732 | 0.2893 |
79
- | 0.5011 | 25.0 | 7200 | 0.5612 | 0.2876 |
80
- | 0.4658 | 26.0 | 7488 | 0.5631 | 0.2915 |
81
- | 0.4423 | 27.0 | 7776 | 0.5668 | 0.2853 |
82
- | 0.4287 | 28.0 | 8064 | 0.5664 | 0.2847 |
83
- | 0.4634 | 29.0 | 8352 | 0.5687 | 0.2875 |
84
- | 0.4413 | 30.0 | 8640 | 0.5684 | 0.2954 |
85
- | 0.4385 | 31.0 | 8928 | 0.5602 | 0.2801 |
86
- | 0.4557 | 32.0 | 9216 | 0.5637 | 0.2747 |
87
- | 0.4344 | 33.0 | 9504 | 0.5690 | 0.2853 |
88
- | 0.4264 | 34.0 | 9792 | 0.5653 | 0.2866 |
89
- | 0.4395 | 35.0 | 10080 | 0.5764 | 0.2808 |
90
- | 0.4278 | 36.0 | 10368 | 0.5758 | 0.2761 |
91
- | 0.44 | 37.0 | 10656 | 0.5816 | 0.2770 |
92
- | 0.4356 | 38.0 | 10944 | 0.5814 | 0.2784 |
93
- | 0.487 | 39.0 | 11232 | 0.5694 | 0.2834 |
94
- | 0.44 | 40.0 | 11520 | 0.5637 | 0.2747 |
95
- | 0.4151 | 41.0 | 11808 | 0.5683 | 0.2763 |
96
- | 0.4208 | 42.0 | 12096 | 0.5720 | 0.2732 |
97
- | 0.4354 | 43.0 | 12384 | 0.5657 | 0.2771 |
98
- | 0.4304 | 44.0 | 12672 | 0.5735 | 0.2724 |
99
- | 0.3991 | 45.0 | 12960 | 0.5638 | 0.2688 |
100
- | 0.4348 | 46.0 | 13248 | 0.5639 | 0.2699 |
101
- | 0.4291 | 47.0 | 13536 | 0.5577 | 0.2682 |
102
- | 0.4252 | 48.0 | 13824 | 0.5611 | 0.2680 |
103
- | 0.4253 | 49.0 | 14112 | 0.5621 | 0.2682 |
104
- | 0.4298 | 50.0 | 14400 | 0.5592 | 0.2671 |
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: 0.5583
18
+ - Wer: 0.2403
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 4e-06
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 2
40
  - seed: 42
41
+ - gradient_accumulation_steps: 2
42
+ - total_train_batch_size: 4
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 500
46
  - num_epochs: 50.0
47
  - mixed_precision_training: Native AMP
48
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
53
+ | 0.4806 | 1.0 | 1154 | 0.5674 | 0.2700 |
54
+ | 0.4109 | 2.0 | 2308 | 0.5667 | 0.2740 |
55
+ | 0.4183 | 3.0 | 3462 | 0.5651 | 0.2742 |
56
+ | 0.4618 | 4.0 | 4616 | 0.5653 | 0.2675 |
57
+ | 0.4179 | 5.0 | 5770 | 0.5541 | 0.2697 |
58
+ | 0.4376 | 6.0 | 6924 | 0.5799 | 0.2691 |
59
+ | 0.4341 | 7.0 | 8078 | 0.5593 | 0.2649 |
60
+ | 0.4234 | 8.0 | 9232 | 0.5489 | 0.2652 |
61
+ | 0.3965 | 9.0 | 10386 | 0.5606 | 0.2601 |
62
+ | 0.4383 | 10.0 | 11540 | 0.5630 | 0.2607 |
63
+ | 0.4245 | 11.0 | 12694 | 0.5647 | 0.2561 |
64
+ | 0.3946 | 12.0 | 13848 | 0.5526 | 0.2635 |
65
+ | 0.3722 | 13.0 | 15002 | 0.5786 | 0.2565 |
66
+ | 0.3558 | 14.0 | 16156 | 0.5589 | 0.2638 |
67
+ | 0.392 | 15.0 | 17310 | 0.5581 | 0.2593 |
68
+ | 0.401 | 16.0 | 18464 | 0.5528 | 0.2566 |
69
+ | 0.4391 | 17.0 | 19618 | 0.5584 | 0.2554 |
70
+ | 0.4082 | 18.0 | 20772 | 0.5610 | 0.2528 |
71
+ | 0.4316 | 19.0 | 21926 | 0.5408 | 0.2507 |
72
+ | 0.3136 | 20.0 | 23080 | 0.5592 | 0.2525 |
73
+ | 0.4249 | 21.0 | 24234 | 0.5684 | 0.2560 |
74
+ | 0.4993 | 22.0 | 25388 | 0.5521 | 0.2529 |
75
+ | 0.4006 | 23.0 | 26542 | 0.5391 | 0.2540 |
76
+ | 0.3415 | 24.0 | 27696 | 0.5622 | 0.2503 |
77
+ | 0.3938 | 25.0 | 28850 | 0.5533 | 0.2541 |
78
+ | 0.4509 | 26.0 | 30004 | 0.5567 | 0.2486 |
79
+ | 0.3583 | 27.0 | 31158 | 0.5641 | 0.2523 |
80
+ | 0.4084 | 28.0 | 32312 | 0.5687 | 0.2521 |
81
+ | 0.3916 | 29.0 | 33466 | 0.5656 | 0.2495 |
82
+ | 0.4298 | 30.0 | 34620 | 0.5718 | 0.2499 |
83
+ | 0.3544 | 31.0 | 35774 | 0.5595 | 0.2445 |
84
+ | 0.3748 | 32.0 | 36928 | 0.5464 | 0.2461 |
85
+ | 0.3839 | 33.0 | 38082 | 0.5652 | 0.2475 |
86
+ | 0.3691 | 34.0 | 39236 | 0.5551 | 0.2428 |
87
+ | 0.3076 | 35.0 | 40390 | 0.5554 | 0.2463 |
88
+ | 0.3886 | 36.0 | 41544 | 0.5588 | 0.2461 |
89
+ | 0.41 | 37.0 | 42698 | 0.5601 | 0.2507 |
90
+ | 0.3595 | 38.0 | 43852 | 0.5645 | 0.2425 |
91
+ | 0.4174 | 39.0 | 45006 | 0.5561 | 0.2422 |
92
+ | 0.3801 | 40.0 | 46160 | 0.5554 | 0.2427 |
93
+ | 0.3513 | 41.0 | 47314 | 0.5599 | 0.2420 |
94
+ | 0.3739 | 42.0 | 48468 | 0.5669 | 0.2418 |
95
+ | 0.3702 | 43.0 | 49622 | 0.5646 | 0.2441 |
96
+ | 0.3444 | 44.0 | 50776 | 0.5658 | 0.2413 |
97
+ | 0.3152 | 45.0 | 51930 | 0.5559 | 0.2402 |
98
+ | 0.4 | 46.0 | 53084 | 0.5599 | 0.2429 |
99
+ | 0.4154 | 47.0 | 54238 | 0.5568 | 0.2430 |
100
+ | 0.3158 | 48.0 | 55392 | 0.5608 | 0.2428 |
101
+ | 0.3577 | 49.0 | 56546 | 0.5593 | 0.2412 |
102
+ | 0.3456 | 50.0 | 57700 | 0.5583 | 0.2403 |
103
 
104
 
105
  ### Framework versions