finetuning-whisper-swahili-asr-model_ndizi-3epochs
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: 1.1302
- Wer: 53.1560
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7364 | 3.6232 | 1000 | 0.8262 | 52.9184 |
| 0.3941 | 7.2464 | 2000 | 0.9396 | 53.3170 |
| 0.1829 | 10.8696 | 3000 | 1.0578 | 51.8262 |
| 0.0965 | 14.4928 | 4000 | 1.1302 | 53.1560 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1