whisper-small-finetuned-fleurs
This model is a fine-tuned version of openai/whisper-small on the Fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.5993
- Wer: 24.0239
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_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0364 | 2.6738 | 500 | 0.4733 | 22.8574 |
| 0.008 | 5.3476 | 1000 | 0.5297 | 23.4937 |
| 0.0033 | 8.0214 | 1500 | 0.5837 | 22.9538 |
| 0.0026 | 10.6952 | 2000 | 0.5993 | 24.0239 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.8.0+cu126
- Datasets 2.16.1
- Tokenizers 0.21.4