Whisper whisper-small sot
This model is a fine-tuned version of openai/whisper-small on the dsfsi-anv/za-african-next-voices dataset. It achieves the following results on the evaluation set:
- Loss: 0.4410
- Wer: 24.8628
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 75
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6639 | 0.25 | 250 | 0.6573 | 36.9818 |
| 0.4406 | 0.5 | 500 | 0.5333 | 29.8496 |
| 0.3337 | 0.75 | 750 | 0.4794 | 25.3273 |
| 0.409 | 1.231 | 1000 | 0.4410 | 24.8628 |
Framework versions
- Transformers 4.52.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.4