ASR_test
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4159
- Wer: 0.2533
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.4026 | 0.5 | 500 | 3.6532 | 0.9993 |
| 2.8688 | 1.0 | 1000 | 1.5272 | 0.7639 |
| 1.2649 | 1.5 | 1500 | 0.7656 | 0.4491 |
| 0.9837 | 2.0 | 2000 | 0.6166 | 0.3621 |
| 0.8149 | 2.5 | 2500 | 0.5369 | 0.3169 |
| 0.768 | 3.0 | 3000 | 0.6136 | 0.2949 |
| 0.6671 | 3.5 | 3500 | 0.4668 | 0.2833 |
| 0.6472 | 4.0 | 4000 | 0.4364 | 0.2633 |
| 0.5917 | 4.5 | 4500 | 0.4242 | 0.2566 |
| 0.5675 | 5.0 | 5000 | 0.4159 | 0.2533 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1