whisper-small-SIT_17_07_26_0805
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: 0.0574
- Wer: 3.6448
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.5659 | 1.0 | 87 | 0.0719 | 4.2412 |
| 0.0505 | 2.0 | 174 | 0.0570 | 3.1146 |
| 0.0203 | 3.0 | 261 | 0.0574 | 3.6448 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 2.19.0
- Tokenizers 0.22.2