Whisper Small - Toki Pona - Test1
This model is a fine-tuned version of openai/whisper-small on the Common Voice 23.0 - Toki Pona dataset. It achieves the following results on the evaluation set:
- Loss: 0.1480
- Wer: 11.1247
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: 8
- 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: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 300
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6651 | 0.3268 | 50 | 0.3995 | 24.0220 |
| 0.1707 | 0.6536 | 100 | 0.2032 | 14.5477 |
| 0.1228 | 0.9804 | 150 | 0.1668 | 13.4474 |
| 0.0699 | 1.3072 | 200 | 0.1560 | 11.2469 |
| 0.0691 | 1.6340 | 250 | 0.1524 | 11.4914 |
| 0.0751 | 1.9608 | 300 | 0.1480 | 11.1247 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.8.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.4