Hugging Face's logo

gary109
/
ai-light-dance_singing3_ft_pretrain2_wav2vec2-large-xlsr-53

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
08fcd81
•
1 Parent(s): 1bd8ec1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +159 -0
README.md ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: ai-light-dance_singing3_ft_pretrain2_wav2vec2-large-xlsr-53
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # ai-light-dance_singing3_ft_pretrain2_wav2vec2-large-xlsr-53
13
+
14
+ This model is a fine-tuned version of [gary109/ai-light-dance_pretrain2_wav2vec2-large-xlsr-53](https://huggingface.co/gary109/ai-light-dance_pretrain2_wav2vec2-large-xlsr-53) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 2.6331
17
+ - Wer: 0.9906
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 8
41
+ - total_train_batch_size: 64
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 100
45
+ - num_epochs: 100.0
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
51
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 2.1979 | 1.0 | 72 | 3.4874 | 0.9922 |
53
+ | 1.9612 | 2.0 | 144 | 4.5105 | 0.9889 |
54
+ | 1.8052 | 3.0 | 216 | 4.0819 | 0.9787 |
55
+ | 1.827 | 4.0 | 288 | 4.4058 | 0.9844 |
56
+ | 1.6249 | 5.0 | 360 | 4.8895 | 0.9872 |
57
+ | 1.6285 | 6.0 | 432 | 4.7534 | 0.9837 |
58
+ | 1.6713 | 7.0 | 504 | 4.5588 | 0.9819 |
59
+ | 1.777 | 8.0 | 576 | 4.7414 | 0.9860 |
60
+ | 1.6759 | 9.0 | 648 | 4.5222 | 0.9874 |
61
+ | 1.5533 | 10.0 | 720 | 3.6153 | 0.9824 |
62
+ | 1.5053 | 11.0 | 792 | 5.6485 | 0.9907 |
63
+ | 1.6541 | 12.0 | 864 | 5.4657 | 0.9843 |
64
+ | 1.5891 | 13.0 | 936 | 4.4534 | 0.9877 |
65
+ | 1.6809 | 14.0 | 1008 | 4.8404 | 0.9891 |
66
+ | 1.5506 | 15.0 | 1080 | 3.7248 | 0.9873 |
67
+ | 1.4754 | 16.0 | 1152 | 4.3970 | 0.9864 |
68
+ | 1.4576 | 17.0 | 1224 | 4.4771 | 0.9855 |
69
+ | 1.5614 | 18.0 | 1296 | 3.5102 | 0.9861 |
70
+ | 1.655 | 19.0 | 1368 | 4.8062 | 0.9863 |
71
+ | 1.455 | 20.0 | 1440 | 5.0790 | 0.9880 |
72
+ | 1.4701 | 21.0 | 1512 | 4.2320 | 0.9850 |
73
+ | 1.495 | 22.0 | 1584 | 5.2132 | 0.9889 |
74
+ | 1.5676 | 23.0 | 1656 | 4.1597 | 0.9806 |
75
+ | 1.5837 | 24.0 | 1728 | 5.0981 | 0.9867 |
76
+ | 1.4437 | 25.0 | 1800 | 3.6791 | 0.9813 |
77
+ | 1.4684 | 26.0 | 1872 | 4.0667 | 0.9869 |
78
+ | 1.4617 | 27.0 | 1944 | 5.2262 | 0.9902 |
79
+ | 1.5259 | 28.0 | 2016 | 4.5763 | 0.9876 |
80
+ | 1.5127 | 29.0 | 2088 | 3.5297 | 0.9831 |
81
+ | 1.4726 | 30.0 | 2160 | 3.2379 | 0.9776 |
82
+ | 1.446 | 31.0 | 2232 | 3.9459 | 0.9835 |
83
+ | 1.4116 | 32.0 | 2304 | 3.5352 | 0.9815 |
84
+ | 1.462 | 33.0 | 2376 | 3.3658 | 0.9761 |
85
+ | 1.498 | 34.0 | 2448 | 3.8620 | 0.9795 |
86
+ | 1.382 | 35.0 | 2520 | 3.4734 | 0.9798 |
87
+ | 1.3969 | 36.0 | 2592 | 3.7285 | 0.9780 |
88
+ | 1.3945 | 37.0 | 2664 | 3.7255 | 0.9820 |
89
+ | 1.4616 | 38.0 | 2736 | 3.8788 | 0.9812 |
90
+ | 1.4791 | 39.0 | 2808 | 3.1891 | 0.9781 |
91
+ | 1.3875 | 40.0 | 2880 | 3.6854 | 0.9801 |
92
+ | 1.3914 | 41.0 | 2952 | 3.4011 | 0.9742 |
93
+ | 1.3744 | 42.0 | 3024 | 3.5792 | 0.9808 |
94
+ | 1.4085 | 43.0 | 3096 | 2.9806 | 0.9743 |
95
+ | 1.407 | 44.0 | 3168 | 3.3188 | 0.9821 |
96
+ | 1.3678 | 45.0 | 3240 | 3.6300 | 0.9817 |
97
+ | 1.3762 | 46.0 | 3312 | 3.0986 | 0.9774 |
98
+ | 1.3507 | 47.0 | 3384 | 2.8956 | 0.9733 |
99
+ | 1.3646 | 48.0 | 3456 | 2.8360 | 0.9731 |
100
+ | 1.4027 | 49.0 | 3528 | 3.5181 | 0.9744 |
101
+ | 1.3383 | 50.0 | 3600 | 3.2710 | 0.9769 |
102
+ | 1.3517 | 51.0 | 3672 | 2.9974 | 0.9756 |
103
+ | 1.3551 | 52.0 | 3744 | 3.3180 | 0.9751 |
104
+ | 1.3493 | 53.0 | 3816 | 2.6087 | 0.9994 |
105
+ | 1.3977 | 54.0 | 3888 | 2.6875 | 0.9778 |
106
+ | 1.3254 | 55.0 | 3960 | 3.3663 | 0.9787 |
107
+ | 1.303 | 56.0 | 4032 | 2.6154 | 0.9692 |
108
+ | 1.2612 | 57.0 | 4104 | 3.2773 | 0.9761 |
109
+ | 1.3161 | 58.0 | 4176 | 2.9020 | 0.9717 |
110
+ | 1.3026 | 59.0 | 4248 | 3.1517 | 0.9709 |
111
+ | 1.262 | 60.0 | 4320 | 3.1299 | 0.9675 |
112
+ | 1.2885 | 61.0 | 4392 | 3.1023 | 0.9724 |
113
+ | 1.2538 | 62.0 | 4464 | 2.7857 | 0.9877 |
114
+ | 1.2536 | 63.0 | 4536 | 3.0150 | 0.9704 |
115
+ | 1.3339 | 64.0 | 4608 | 2.9305 | 0.9722 |
116
+ | 1.2392 | 65.0 | 4680 | 2.7695 | 0.9749 |
117
+ | 1.2572 | 66.0 | 4752 | 2.8677 | 0.9689 |
118
+ | 1.2538 | 67.0 | 4824 | 2.8597 | 0.9805 |
119
+ | 1.2355 | 68.0 | 4896 | 2.8300 | 0.9788 |
120
+ | 1.2682 | 69.0 | 4968 | 2.7011 | 0.9742 |
121
+ | 1.2252 | 70.0 | 5040 | 2.8322 | 0.9722 |
122
+ | 1.2085 | 71.0 | 5112 | 2.7401 | 0.9711 |
123
+ | 1.2412 | 72.0 | 5184 | 2.6227 | 0.9763 |
124
+ | 1.2148 | 73.0 | 5256 | 2.7146 | 0.9690 |
125
+ | 1.2411 | 74.0 | 5328 | 2.9963 | 0.9663 |
126
+ | 1.2012 | 75.0 | 5400 | 2.7940 | 0.9655 |
127
+ | 1.1969 | 76.0 | 5472 | 2.6212 | 0.9790 |
128
+ | 1.2004 | 77.0 | 5544 | 2.8644 | 0.9711 |
129
+ | 1.2247 | 78.0 | 5616 | 2.6127 | 0.9621 |
130
+ | 1.2791 | 79.0 | 5688 | 2.6538 | 0.9719 |
131
+ | 1.1867 | 80.0 | 5760 | 2.7779 | 0.9587 |
132
+ | 1.1992 | 81.0 | 5832 | 2.8297 | 0.9643 |
133
+ | 1.1833 | 82.0 | 5904 | 2.8508 | 0.9723 |
134
+ | 1.2092 | 83.0 | 5976 | 2.8261 | 0.9690 |
135
+ | 1.2215 | 84.0 | 6048 | 2.5995 | 0.9717 |
136
+ | 1.1966 | 85.0 | 6120 | 2.7659 | 0.9677 |
137
+ | 1.1774 | 86.0 | 6192 | 2.6289 | 0.9703 |
138
+ | 1.2002 | 87.0 | 6264 | 2.7197 | 0.9775 |
139
+ | 1.2035 | 88.0 | 6336 | 2.6154 | 0.9778 |
140
+ | 1.2219 | 89.0 | 6408 | 2.6426 | 0.9761 |
141
+ | 1.1724 | 90.0 | 6480 | 2.5996 | 0.9801 |
142
+ | 1.1832 | 91.0 | 6552 | 2.7315 | 0.9743 |
143
+ | 1.1759 | 92.0 | 6624 | 2.5726 | 0.9965 |
144
+ | 1.1638 | 93.0 | 6696 | 2.6570 | 0.9865 |
145
+ | 1.1872 | 94.0 | 6768 | 2.6414 | 0.9948 |
146
+ | 1.144 | 95.0 | 6840 | 2.6264 | 0.9863 |
147
+ | 1.1636 | 96.0 | 6912 | 2.5820 | 0.9918 |
148
+ | 1.1714 | 97.0 | 6984 | 2.5970 | 0.9913 |
149
+ | 1.1943 | 98.0 | 7056 | 2.6308 | 0.9895 |
150
+ | 1.185 | 99.0 | 7128 | 2.6379 | 0.9898 |
151
+ | 1.1569 | 100.0 | 7200 | 2.6331 | 0.9906 |
152
+
153
+
154
+ ### Framework versions
155
+
156
+ - Transformers 4.21.0.dev0
157
+ - Pytorch 1.9.1+cu102
158
+ - Datasets 2.3.3.dev0
159
+ - Tokenizers 0.12.1