metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
results: []
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 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6777
- Wer: 0.4204
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.6227 | 1.0 | 72 | 0.7283 | 0.4659 |
0.6027 | 2.0 | 144 | 0.7168 | 0.4428 |
0.5973 | 3.0 | 216 | 0.7061 | 0.4313 |
0.5773 | 4.0 | 288 | 0.7068 | 0.4336 |
0.5965 | 5.0 | 360 | 0.7038 | 0.4340 |
0.5854 | 6.0 | 432 | 0.7054 | 0.4309 |
0.5832 | 7.0 | 504 | 0.6990 | 0.4253 |
0.5968 | 8.0 | 576 | 0.6988 | 0.4232 |
0.5895 | 9.0 | 648 | 0.6867 | 0.4222 |
0.6378 | 10.0 | 720 | 0.6777 | 0.4204 |
Framework versions
- Transformers 4.21.0.dev0
- Pytorch 1.9.1+cu102
- Datasets 2.3.3.dev0
- Tokenizers 0.12.1