whisper-base-bungoma.en
This model is a fine-tuned version of openai/whisper-base.en on the Azure-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0636
- Wer: 25.2804
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7399 | 1.38 | 250 | 0.2390 | 29.3356 |
| 0.2829 | 2.76 | 500 | 0.0774 | 21.8292 |
| 0.1573 | 4.14 | 750 | 0.0921 | 22.8645 |
| 0.1373 | 5.52 | 1000 | 0.0636 | 25.2804 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2