Whisper Base N - Fine-Tuned
This model is a fine-tuned version of openai/whisper-base on the N Demo dataset. It achieves the following results on the evaluation set:
- Loss: 0.8417
- Wer: 85.6884
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 OptimizerNames.ADAMW_TORCH_FUSED 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: 20
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.9371 | 0.4717 | 25 | 1.2807 | 107.6087 |
| 1.1246 | 0.9434 | 50 | 0.9736 | 93.8406 |
| 0.8861 | 1.4151 | 75 | 0.8757 | 86.0507 |
| 0.8158 | 1.8868 | 100 | 0.8417 | 85.6884 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.9.0+cu126
- Datasets 4.5.0
- Tokenizers 0.22.2