update model card README.md
Browse files
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
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Wer: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,7 +34,7 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate:
|
40 |
- train_batch_size: 4
|
41 |
- eval_batch_size: 4
|
42 |
- seed: 42
|
@@ -44,34 +42,64 @@ The following hyperparameters were used during training:
|
|
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:
|
48 |
-
- num_epochs:
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch | Step
|
54 |
-
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
|
76 |
|
77 |
### 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: 0.5592
|
18 |
+
- Wer: 0.2671
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 8e-06
|
38 |
- train_batch_size: 4
|
39 |
- eval_batch_size: 4
|
40 |
- seed: 42
|
|
|
42 |
- total_train_batch_size: 16
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 5000
|
46 |
+
- num_epochs: 50.0
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
53 |
+
| 0.4853 | 1.0 | 288 | 0.5760 | 0.3098 |
|
54 |
+
| 0.48 | 2.0 | 576 | 0.5787 | 0.3085 |
|
55 |
+
| 0.4625 | 3.0 | 864 | 0.5925 | 0.3112 |
|
56 |
+
| 0.4704 | 4.0 | 1152 | 0.6065 | 0.3108 |
|
57 |
+
| 0.4854 | 5.0 | 1440 | 0.6036 | 0.3112 |
|
58 |
+
| 0.4918 | 6.0 | 1728 | 0.6007 | 0.3148 |
|
59 |
+
| 0.4549 | 7.0 | 2016 | 0.6039 | 0.3073 |
|
60 |
+
| 0.4546 | 8.0 | 2304 | 0.6129 | 0.3073 |
|
61 |
+
| 0.4404 | 9.0 | 2592 | 0.6062 | 0.3054 |
|
62 |
+
| 0.4681 | 10.0 | 2880 | 0.6063 | 0.3075 |
|
63 |
+
| 0.469 | 11.0 | 3168 | 0.5881 | 0.3031 |
|
64 |
+
| 0.4903 | 12.0 | 3456 | 0.5913 | 0.3047 |
|
65 |
+
| 0.4677 | 13.0 | 3744 | 0.5921 | 0.3055 |
|
66 |
+
| 0.502 | 14.0 | 4032 | 0.5905 | 0.3042 |
|
67 |
+
| 0.5028 | 15.0 | 4320 | 0.5989 | 0.3088 |
|
68 |
+
| 0.4706 | 16.0 | 4608 | 0.5665 | 0.3066 |
|
69 |
+
| 0.4839 | 17.0 | 4896 | 0.6003 | 0.3111 |
|
70 |
+
| 0.4733 | 18.0 | 5184 | 0.5937 | 0.3039 |
|
71 |
+
| 0.4544 | 19.0 | 5472 | 0.5903 | 0.3025 |
|
72 |
+
| 0.4616 | 20.0 | 5760 | 0.6064 | 0.2968 |
|
73 |
+
| 0.475 | 21.0 | 6048 | 0.5883 | 0.2960 |
|
74 |
+
| 0.4707 | 22.0 | 6336 | 0.5900 | 0.2888 |
|
75 |
+
| 0.4562 | 23.0 | 6624 | 0.5642 | 0.2956 |
|
76 |
+
| 0.455 | 24.0 | 6912 | 0.5732 | 0.2893 |
|
77 |
+
| 0.5011 | 25.0 | 7200 | 0.5612 | 0.2876 |
|
78 |
+
| 0.4658 | 26.0 | 7488 | 0.5631 | 0.2915 |
|
79 |
+
| 0.4423 | 27.0 | 7776 | 0.5668 | 0.2853 |
|
80 |
+
| 0.4287 | 28.0 | 8064 | 0.5664 | 0.2847 |
|
81 |
+
| 0.4634 | 29.0 | 8352 | 0.5687 | 0.2875 |
|
82 |
+
| 0.4413 | 30.0 | 8640 | 0.5684 | 0.2954 |
|
83 |
+
| 0.4385 | 31.0 | 8928 | 0.5602 | 0.2801 |
|
84 |
+
| 0.4557 | 32.0 | 9216 | 0.5637 | 0.2747 |
|
85 |
+
| 0.4344 | 33.0 | 9504 | 0.5690 | 0.2853 |
|
86 |
+
| 0.4264 | 34.0 | 9792 | 0.5653 | 0.2866 |
|
87 |
+
| 0.4395 | 35.0 | 10080 | 0.5764 | 0.2808 |
|
88 |
+
| 0.4278 | 36.0 | 10368 | 0.5758 | 0.2761 |
|
89 |
+
| 0.44 | 37.0 | 10656 | 0.5816 | 0.2770 |
|
90 |
+
| 0.4356 | 38.0 | 10944 | 0.5814 | 0.2784 |
|
91 |
+
| 0.487 | 39.0 | 11232 | 0.5694 | 0.2834 |
|
92 |
+
| 0.44 | 40.0 | 11520 | 0.5637 | 0.2747 |
|
93 |
+
| 0.4151 | 41.0 | 11808 | 0.5683 | 0.2763 |
|
94 |
+
| 0.4208 | 42.0 | 12096 | 0.5720 | 0.2732 |
|
95 |
+
| 0.4354 | 43.0 | 12384 | 0.5657 | 0.2771 |
|
96 |
+
| 0.4304 | 44.0 | 12672 | 0.5735 | 0.2724 |
|
97 |
+
| 0.3991 | 45.0 | 12960 | 0.5638 | 0.2688 |
|
98 |
+
| 0.4348 | 46.0 | 13248 | 0.5639 | 0.2699 |
|
99 |
+
| 0.4291 | 47.0 | 13536 | 0.5577 | 0.2682 |
|
100 |
+
| 0.4252 | 48.0 | 13824 | 0.5611 | 0.2680 |
|
101 |
+
| 0.4253 | 49.0 | 14112 | 0.5621 | 0.2682 |
|
102 |
+
| 0.4298 | 50.0 | 14400 | 0.5592 | 0.2671 |
|
103 |
|
104 |
|
105 |
### Framework versions
|