whisper-small-tr-best
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: 0.3166
- Wer: 26.3414
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2521 | 0.89 | 1000 | 0.4176 | 37.0010 |
| 0.1283 | 1.77 | 2000 | 0.3558 | 30.5661 |
| 0.0512 | 2.66 | 3000 | 0.3270 | 29.3765 |
| 0.0151 | 3.54 | 4000 | 0.3166 | 26.3414 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0