whisper-small-SIT_18_07_26_0551
This model is a fine-tuned version of Pengwin30/whisper-small-fine-tuned on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0578
- Wer: 3.5785
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: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.5763 | 1.0 | 87 | 0.0697 | 3.9099 |
| 0.0529 | 2.0 | 174 | 0.0568 | 4.0424 |
| 0.0202 | 3.0 | 261 | 0.0596 | 3.4460 |
| 0.0073 | 4.0 | 348 | 0.0575 | 3.7773 |
| 0.0037 | 5.0 | 435 | 0.0578 | 3.5785 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 2.19.0
- Tokenizers 0.22.2