Whisper Small Podcast Fillers
This model is a fine-tuned version of openai/whisper-small on the Podcast Fillers dataset. It achieves the following results on the evaluation set:
- Loss: 0.5077
- Wer: 21.0899
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_BNB 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1333 | 0.0575 | 1000 | 0.3405 | 20.8402 |
| 0.0489 | 0.1151 | 2000 | 0.3946 | 20.4906 |
| 0.0156 | 0.1726 | 3000 | 0.4630 | 20.7675 |
| 0.0141 | 0.2301 | 4000 | 0.5077 | 21.0899 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1