whisper-small-yoruba-lora
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2035
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: 0.001
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.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_ratio: 0.1
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6545 | 0.8989 | 2000 | 0.6119 |
| 0.5771 | 1.7978 | 4000 | 0.5680 |
| 0.5156 | 2.6966 | 6000 | 0.4931 |
| 0.3813 | 3.5955 | 8000 | 0.4293 |
| 0.3119 | 4.4944 | 10000 | 0.3719 |
| 0.2177 | 5.3933 | 12000 | 0.3084 |
| 0.1305 | 6.2921 | 14000 | 0.2485 |
| 0.0542 | 7.1910 | 16000 | 0.2035 |
Framework versions
- PEFT 0.14.0
- Transformers 4.50.3
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4