update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
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](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: 0.7044
|
18 |
+
- Wer: 0.4757
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 8
|
42 |
+
- total_train_batch_size: 64
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 50
|
46 |
+
- num_epochs: 10.0
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
53 |
+
| 1.0489 | 1.0 | 72 | 0.9702 | 0.6696 |
|
54 |
+
| 0.9699 | 2.0 | 144 | 0.9321 | 0.6596 |
|
55 |
+
| 0.9074 | 3.0 | 216 | 0.8542 | 0.6139 |
|
56 |
+
| 0.8979 | 4.0 | 288 | 0.8187 | 0.5777 |
|
57 |
+
| 0.8363 | 5.0 | 360 | 0.7735 | 0.5551 |
|
58 |
+
| 0.802 | 6.0 | 432 | 0.7766 | 0.5402 |
|
59 |
+
| 0.7702 | 7.0 | 504 | 0.7471 | 0.4971 |
|
60 |
+
| 0.7483 | 8.0 | 576 | 0.7226 | 0.4981 |
|
61 |
+
| 0.7196 | 9.0 | 648 | 0.7095 | 0.4842 |
|
62 |
+
| 0.731 | 10.0 | 720 | 0.7044 | 0.4757 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.21.0.dev0
|
68 |
+
- Pytorch 1.9.1+cu102
|
69 |
+
- Datasets 2.3.3.dev0
|
70 |
+
- Tokenizers 0.12.1
|