Hausa BG Finetuned Whisper Small - Ibrahim Ibrahim
This model is a fine-tuned version of openai/whisper-small on the Common Voice, Google Fleurs And Sample Of Bible Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.3793
- Wer Ortho: 25.9471
- Wer: 22.0554
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: 16
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.397 | 0.6658 | 500 | 0.4568 | 31.1958 | 27.1182 |
| 0.2204 | 1.3316 | 1000 | 0.3793 | 25.9471 | 22.0554 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3