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
|
@@ -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
|
16 |
|
17 |
-
This model is a fine-tuned version of [gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53](https://huggingface.co/gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53) on the
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 1.
|
20 |
-
- Wer: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,12 +34,12 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate: 5e-06
|
40 |
- train_batch_size: 8
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
43 |
-
- gradient_accumulation_steps:
|
44 |
-
- total_train_batch_size:
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_steps: 100
|
@@ -52,36 +50,36 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
|
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
| 1.
|
73 |
-
| 1.
|
74 |
-
| 1.
|
75 |
-
| 1.
|
76 |
-
| 1.
|
77 |
-
| 1.
|
78 |
-
| 1.
|
79 |
-
| 1.
|
80 |
-
| 1.
|
81 |
-
| 1.
|
82 |
-
| 1.
|
83 |
-
| 1.
|
84 |
-
| 1.
|
85 |
|
86 |
|
87 |
### 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
|
|
|
12 |
|
13 |
# ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53
|
14 |
|
15 |
+
This model is a fine-tuned version of [gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53](https://huggingface.co/gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.4516
|
18 |
+
- Wer: 0.9094
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2.5e-06
|
38 |
- train_batch_size: 8
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 2
|
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: 100
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
53 |
+
| 1.5782 | 1.0 | 289 | 1.7392 | 0.9268 |
|
54 |
+
| 1.516 | 2.0 | 578 | 1.8778 | 0.9967 |
|
55 |
+
| 1.4542 | 3.0 | 867 | 1.7856 | 0.9860 |
|
56 |
+
| 1.4359 | 4.0 | 1156 | 1.6145 | 0.9181 |
|
57 |
+
| 1.416 | 5.0 | 1445 | 1.6474 | 0.9514 |
|
58 |
+
| 1.3953 | 6.0 | 1734 | 1.7028 | 0.9767 |
|
59 |
+
| 1.361 | 7.0 | 2023 | 1.5753 | 0.9281 |
|
60 |
+
| 1.3778 | 8.0 | 2312 | 1.5564 | 0.9580 |
|
61 |
+
| 1.3472 | 9.0 | 2601 | 1.5750 | 0.9479 |
|
62 |
+
| 1.3454 | 10.0 | 2890 | 1.5264 | 0.9274 |
|
63 |
+
| 1.2984 | 11.0 | 3179 | 1.5087 | 0.9263 |
|
64 |
+
| 1.2852 | 12.0 | 3468 | 1.5042 | 0.9252 |
|
65 |
+
| 1.2744 | 13.0 | 3757 | 1.4865 | 0.9207 |
|
66 |
+
| 1.2874 | 14.0 | 4046 | 1.4923 | 0.9224 |
|
67 |
+
| 1.2698 | 15.0 | 4335 | 1.5070 | 0.9270 |
|
68 |
+
| 1.2661 | 16.0 | 4624 | 1.4819 | 0.9218 |
|
69 |
+
| 1.2572 | 17.0 | 4913 | 1.5565 | 0.9495 |
|
70 |
+
| 1.256 | 18.0 | 5202 | 1.4995 | 0.9071 |
|
71 |
+
| 1.216 | 19.0 | 5491 | 1.5129 | 0.9274 |
|
72 |
+
| 1.286 | 20.0 | 5780 | 1.4750 | 0.9203 |
|
73 |
+
| 1.2328 | 21.0 | 6069 | 1.4861 | 0.9267 |
|
74 |
+
| 1.2085 | 22.0 | 6358 | 1.4780 | 0.9109 |
|
75 |
+
| 1.2207 | 23.0 | 6647 | 1.4626 | 0.9130 |
|
76 |
+
| 1.1843 | 24.0 | 6936 | 1.4453 | 0.9067 |
|
77 |
+
| 1.2232 | 25.0 | 7225 | 1.4827 | 0.9186 |
|
78 |
+
| 1.232 | 26.0 | 7514 | 1.4358 | 0.8973 |
|
79 |
+
| 1.1891 | 27.0 | 7803 | 1.4377 | 0.8954 |
|
80 |
+
| 1.1856 | 28.0 | 8092 | 1.4420 | 0.9022 |
|
81 |
+
| 1.219 | 29.0 | 8381 | 1.4593 | 0.9101 |
|
82 |
+
| 1.2075 | 30.0 | 8670 | 1.4516 | 0.9094 |
|
83 |
|
84 |
|
85 |
### Framework versions
|