|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1 |
|
|
|
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. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5592 |
|
- Wer: 0.2671 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 8e-06 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 5000 |
|
- num_epochs: 50.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| 0.4853 | 1.0 | 288 | 0.5760 | 0.3098 | |
|
| 0.48 | 2.0 | 576 | 0.5787 | 0.3085 | |
|
| 0.4625 | 3.0 | 864 | 0.5925 | 0.3112 | |
|
| 0.4704 | 4.0 | 1152 | 0.6065 | 0.3108 | |
|
| 0.4854 | 5.0 | 1440 | 0.6036 | 0.3112 | |
|
| 0.4918 | 6.0 | 1728 | 0.6007 | 0.3148 | |
|
| 0.4549 | 7.0 | 2016 | 0.6039 | 0.3073 | |
|
| 0.4546 | 8.0 | 2304 | 0.6129 | 0.3073 | |
|
| 0.4404 | 9.0 | 2592 | 0.6062 | 0.3054 | |
|
| 0.4681 | 10.0 | 2880 | 0.6063 | 0.3075 | |
|
| 0.469 | 11.0 | 3168 | 0.5881 | 0.3031 | |
|
| 0.4903 | 12.0 | 3456 | 0.5913 | 0.3047 | |
|
| 0.4677 | 13.0 | 3744 | 0.5921 | 0.3055 | |
|
| 0.502 | 14.0 | 4032 | 0.5905 | 0.3042 | |
|
| 0.5028 | 15.0 | 4320 | 0.5989 | 0.3088 | |
|
| 0.4706 | 16.0 | 4608 | 0.5665 | 0.3066 | |
|
| 0.4839 | 17.0 | 4896 | 0.6003 | 0.3111 | |
|
| 0.4733 | 18.0 | 5184 | 0.5937 | 0.3039 | |
|
| 0.4544 | 19.0 | 5472 | 0.5903 | 0.3025 | |
|
| 0.4616 | 20.0 | 5760 | 0.6064 | 0.2968 | |
|
| 0.475 | 21.0 | 6048 | 0.5883 | 0.2960 | |
|
| 0.4707 | 22.0 | 6336 | 0.5900 | 0.2888 | |
|
| 0.4562 | 23.0 | 6624 | 0.5642 | 0.2956 | |
|
| 0.455 | 24.0 | 6912 | 0.5732 | 0.2893 | |
|
| 0.5011 | 25.0 | 7200 | 0.5612 | 0.2876 | |
|
| 0.4658 | 26.0 | 7488 | 0.5631 | 0.2915 | |
|
| 0.4423 | 27.0 | 7776 | 0.5668 | 0.2853 | |
|
| 0.4287 | 28.0 | 8064 | 0.5664 | 0.2847 | |
|
| 0.4634 | 29.0 | 8352 | 0.5687 | 0.2875 | |
|
| 0.4413 | 30.0 | 8640 | 0.5684 | 0.2954 | |
|
| 0.4385 | 31.0 | 8928 | 0.5602 | 0.2801 | |
|
| 0.4557 | 32.0 | 9216 | 0.5637 | 0.2747 | |
|
| 0.4344 | 33.0 | 9504 | 0.5690 | 0.2853 | |
|
| 0.4264 | 34.0 | 9792 | 0.5653 | 0.2866 | |
|
| 0.4395 | 35.0 | 10080 | 0.5764 | 0.2808 | |
|
| 0.4278 | 36.0 | 10368 | 0.5758 | 0.2761 | |
|
| 0.44 | 37.0 | 10656 | 0.5816 | 0.2770 | |
|
| 0.4356 | 38.0 | 10944 | 0.5814 | 0.2784 | |
|
| 0.487 | 39.0 | 11232 | 0.5694 | 0.2834 | |
|
| 0.44 | 40.0 | 11520 | 0.5637 | 0.2747 | |
|
| 0.4151 | 41.0 | 11808 | 0.5683 | 0.2763 | |
|
| 0.4208 | 42.0 | 12096 | 0.5720 | 0.2732 | |
|
| 0.4354 | 43.0 | 12384 | 0.5657 | 0.2771 | |
|
| 0.4304 | 44.0 | 12672 | 0.5735 | 0.2724 | |
|
| 0.3991 | 45.0 | 12960 | 0.5638 | 0.2688 | |
|
| 0.4348 | 46.0 | 13248 | 0.5639 | 0.2699 | |
|
| 0.4291 | 47.0 | 13536 | 0.5577 | 0.2682 | |
|
| 0.4252 | 48.0 | 13824 | 0.5611 | 0.2680 | |
|
| 0.4253 | 49.0 | 14112 | 0.5621 | 0.2682 | |
|
| 0.4298 | 50.0 | 14400 | 0.5592 | 0.2671 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.0.dev0 |
|
- Pytorch 1.9.1+cu102 |
|
- Datasets 2.3.3.dev0 |
|
- Tokenizers 0.12.1 |
|
|
