whisper-small-nigerian-en
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: 0.1917
- Wer: 8.2943
- Wer Normalized: 5.2181
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- 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: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Wer Normalized |
|---|---|---|---|---|---|
| 7.2858 | 0.8040 | 100 | 0.3781 | 11.3985 | 7.2799 |
| 1.6666 | 1.6030 | 200 | 0.2012 | 9.3129 | 6.1221 |
| 0.4446 | 2.4020 | 300 | 0.1960 | 8.3751 | 5.4718 |
| 0.1887 | 3.2010 | 400 | 0.1917 | 8.2943 | 5.2181 |
| 0.1594 | 4.0 | 500 | 0.1933 | 7.9709 | 5.2498 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 2.21.0
- Tokenizers 0.22.2