Whisper-Small-Tl - LWobole
This model is a fine-tuned version of openai/whisper-small on the fleurs-fil_ph dataset. It achieves the following results on the evaluation set:
- Loss: 0.3868
- Wer: 16.0433
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 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: 800
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2124 | 1.3889 | 200 | 0.3847 | 18.5317 |
| 0.0993 | 2.7778 | 400 | 0.3647 | 16.8689 |
| 0.0289 | 4.1667 | 600 | 0.3793 | 16.0278 |
| 0.019 | 5.5556 | 800 | 0.3868 | 16.0433 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.2.1+cu121
- Datasets 3.5.0
- Tokenizers 0.21.1