update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: ai-light-dance_singing5_ft_wav2vec2-large-xlsr-53-5gram-v4-2-1
|
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_singing5_ft_wav2vec2-large-xlsr-53-5gram-v4-2-1
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [gary109/ai-light-dance_singing4_ft_wav2vec2-large-xlsr-53-5gram-v4-2-1](https://huggingface.co/gary109/ai-light-dance_singing4_ft_wav2vec2-large-xlsr-53-5gram-v4-2-1) on the None dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.1774
|
17 |
+
- Wer: 0.0836
|
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: 4e-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: 50.0
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
52 |
+
| 0.4351 | 1.0 | 100 | 0.1948 | 0.0903 |
|
53 |
+
| 0.4381 | 2.0 | 200 | 0.1961 | 0.0930 |
|
54 |
+
| 0.441 | 3.0 | 300 | 0.1948 | 0.0957 |
|
55 |
+
| 0.453 | 4.0 | 400 | 0.1971 | 0.0905 |
|
56 |
+
| 0.4324 | 5.0 | 500 | 0.1823 | 0.0879 |
|
57 |
+
| 0.4561 | 6.0 | 600 | 0.1934 | 0.0893 |
|
58 |
+
| 0.4231 | 7.0 | 700 | 0.2088 | 0.0977 |
|
59 |
+
| 0.4339 | 8.0 | 800 | 0.1924 | 0.0856 |
|
60 |
+
| 0.4195 | 9.0 | 900 | 0.1835 | 0.0846 |
|
61 |
+
| 0.4162 | 10.0 | 1000 | 0.1869 | 0.0908 |
|
62 |
+
| 0.411 | 11.0 | 1100 | 0.1966 | 0.0950 |
|
63 |
+
| 0.4034 | 12.0 | 1200 | 0.1890 | 0.0879 |
|
64 |
+
| 0.4155 | 13.0 | 1300 | 0.1844 | 0.0915 |
|
65 |
+
| 0.4123 | 14.0 | 1400 | 0.1849 | 0.0891 |
|
66 |
+
| 0.4002 | 15.0 | 1500 | 0.1901 | 0.0902 |
|
67 |
+
| 0.3983 | 16.0 | 1600 | 0.1879 | 0.0865 |
|
68 |
+
| 0.3907 | 17.0 | 1700 | 0.1863 | 0.0856 |
|
69 |
+
| 0.3969 | 18.0 | 1800 | 0.1773 | 0.0836 |
|
70 |
+
| 0.3721 | 19.0 | 1900 | 0.1834 | 0.0890 |
|
71 |
+
| 0.3987 | 20.0 | 2000 | 0.1817 | 0.0852 |
|
72 |
+
| 0.3863 | 21.0 | 2100 | 0.1898 | 0.0914 |
|
73 |
+
| 0.4052 | 22.0 | 2200 | 0.1882 | 0.0857 |
|
74 |
+
| 0.3811 | 23.0 | 2300 | 0.1874 | 0.0856 |
|
75 |
+
| 0.3791 | 24.0 | 2400 | 0.1932 | 0.0885 |
|
76 |
+
| 0.3919 | 25.0 | 2500 | 0.1847 | 0.0815 |
|
77 |
+
| 0.3891 | 26.0 | 2600 | 0.1850 | 0.0852 |
|
78 |
+
| 0.3719 | 27.0 | 2700 | 0.1774 | 0.0820 |
|
79 |
+
| 0.3791 | 28.0 | 2800 | 0.1756 | 0.0825 |
|
80 |
+
| 0.3537 | 29.0 | 2900 | 0.1797 | 0.0844 |
|
81 |
+
| 0.361 | 30.0 | 3000 | 0.1818 | 0.0834 |
|
82 |
+
| 0.3619 | 31.0 | 3100 | 0.1747 | 0.0838 |
|
83 |
+
| 0.3626 | 32.0 | 3200 | 0.1773 | 0.0844 |
|
84 |
+
| 0.3632 | 33.0 | 3300 | 0.1775 | 0.0825 |
|
85 |
+
| 0.3666 | 34.0 | 3400 | 0.1835 | 0.0859 |
|
86 |
+
| 0.3581 | 35.0 | 3500 | 0.1859 | 0.0868 |
|
87 |
+
| 0.3665 | 36.0 | 3600 | 0.1741 | 0.0849 |
|
88 |
+
| 0.3495 | 37.0 | 3700 | 0.1790 | 0.0837 |
|
89 |
+
| 0.3509 | 38.0 | 3800 | 0.1782 | 0.0841 |
|
90 |
+
| 0.3621 | 39.0 | 3900 | 0.1759 | 0.0841 |
|
91 |
+
| 0.3415 | 40.0 | 4000 | 0.1796 | 0.0851 |
|
92 |
+
| 0.3508 | 41.0 | 4100 | 0.1777 | 0.0821 |
|
93 |
+
| 0.3493 | 42.0 | 4200 | 0.1758 | 0.0829 |
|
94 |
+
| 0.359 | 43.0 | 4300 | 0.1788 | 0.0848 |
|
95 |
+
| 0.3438 | 44.0 | 4400 | 0.1782 | 0.0836 |
|
96 |
+
| 0.3642 | 45.0 | 4500 | 0.1732 | 0.0831 |
|
97 |
+
| 0.3456 | 46.0 | 4600 | 0.1768 | 0.0823 |
|
98 |
+
| 0.3532 | 47.0 | 4700 | 0.1735 | 0.0834 |
|
99 |
+
| 0.3448 | 48.0 | 4800 | 0.1755 | 0.0827 |
|
100 |
+
| 0.3487 | 49.0 | 4900 | 0.1767 | 0.0833 |
|
101 |
+
| 0.3427 | 50.0 | 5000 | 0.1774 | 0.0836 |
|
102 |
+
|
103 |
+
|
104 |
+
### Framework versions
|
105 |
+
|
106 |
+
- Transformers 4.21.0.dev0
|
107 |
+
- Pytorch 1.9.1+cu102
|
108 |
+
- Datasets 2.3.3.dev0
|
109 |
+
- Tokenizers 0.12.1
|