whisper-small-pa-round3
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3538
- Wer: 39.1210
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0238 | 4.9020 | 250 | 0.2372 | 40.0705 |
| 0.0064 | 9.8039 | 500 | 0.3321 | 41.1557 |
| 0.0012 | 14.7059 | 750 | 0.3572 | 40.9658 |
| 0.0001 | 19.6078 | 1000 | 0.3538 | 39.1210 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.9.1+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
- Downloads last month
- 3