whisper-tiny-yoruba-v2
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3576
- Wer Ortho: 5.3698
- Cer Ortho: 3.9789
- Wer: 4.9073
- Cer: 3.9929
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 OptimizerNames.ADAMW_TORCH_FUSED 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: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Cer Ortho | Wer | Cer |
|---|---|---|---|---|---|---|---|
| 5.7020 | 1.0 | 2331 | 4.0568 | 6.8658 | 4.8697 | 6.3524 | 4.7782 |
| 3.8030 | 2.0 | 4662 | 3.6074 | 5.7532 | 3.7932 | 5.2627 | 3.8623 |
| 3.4080 | 3.0 | 6993 | 3.3576 | 5.3698 | 3.9789 | 4.9073 | 3.9929 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2