whisper-small-indonesian-disaster-vanilla-0-9
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2759
- Wer: 11.3636
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0027 | 9.3458 | 1000 | 0.2385 | 11.3961 |
| 0.0004 | 18.6916 | 2000 | 0.2511 | 11.2987 |
| 0.0002 | 28.0374 | 3000 | 0.2645 | 11.5260 |
| 0.0001 | 37.3832 | 4000 | 0.2724 | 11.2987 |
| 0.0001 | 46.7290 | 5000 | 0.2759 | 11.3636 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.8.0+cu128
- Datasets 3.0.1
- Tokenizers 0.20.0