whisper-small-ml
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 ml dataset. It achieves the following results on the evaluation set:
- Loss: 0.5906
- Wer: 38.8889
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 adamw_torch 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: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0002 | 37.001 | 1000 | 0.5906 | 38.8889 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.4.0+cu121
- Datasets 3.3.2
- Tokenizers 0.21.0