whisper-small-pl-epoch
This model is a fine-tuned version of openai/whisper-small on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7211
- Wer: 46.8468
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: 16
- 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
- lr_scheduler_warmup_steps: 1000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.2451 | 1.0 | 3 | 0.6515 | 29.7297 |
| 0.3551 | 2.0 | 6 | 0.5899 | 35.1351 |
| 0.0815 | 3.0 | 9 | 0.6503 | 42.3423 |
| 0.0328 | 4.0 | 12 | 0.6936 | 47.7477 |
| 0.0175 | 5.0 | 15 | 0.7211 | 46.8468 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0