openai-whisper_small-horoscope-augumented-poc
This model is a fine-tuned version of openai/whisper-small on the IoanaLivia/horoscope_dataset_augumented dataset. It achieves the following results on the evaluation set:
- Loss: 0.1728
- Wer: 12.2342
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: 416
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.351 | 0.9905 | 104 | 0.2981 | 20.4458 |
| 0.1763 | 1.9810 | 208 | 0.1979 | 14.0661 |
| 0.1197 | 2.9714 | 312 | 0.1787 | 12.7082 |
| 0.0722 | 3.9619 | 416 | 0.1728 | 12.2342 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0