whisper-small-twi-v1
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4264
- Wer Ortho: 29.9227
- Wer: 25.5518
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: 32
- eval_batch_size: 16
- 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: 300
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.4414 | 1.4368 | 500 | 0.4210 | 31.2416 | 26.9385 |
| 0.3449 | 2.8736 | 1000 | 0.3724 | 28.8726 | 24.7855 |
| 0.2134 | 4.3103 | 1500 | 0.3763 | 29.1037 | 25.0021 |
| 0.1751 | 5.7471 | 2000 | 0.3887 | 29.2717 | 24.9063 |
| 0.1140 | 7.1839 | 2500 | 0.4155 | 29.8303 | 25.5809 |
| 0.1024 | 8.6207 | 3000 | 0.4264 | 29.9227 | 25.5518 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2