whisper-small-be2en
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1618
- Bleu: 0.9
- Chrf: 34.0
- Wer: 97.1429
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- 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: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Wer |
|---|---|---|---|---|---|---|
| 2.1697 | 1.0 | 1 | 2.1582 | 0.47 | 0.26 | 117.1429 |
| 2.1697 | 2.0 | 2 | 0.2310 | 0.0 | 0.0 | 100.0 |
| 0.229 | 3.0 | 3 | 0.1618 | 0.9 | 34.0 | 97.1429 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1