finetuning-whisper-small-swahili-ablation_ndizi_FLEURS
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: 0.8979
- Wer: 51.6422
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6343 | 2.1369 | 1000 | 0.8026 | 53.0525 |
| 0.4098 | 4.2738 | 2000 | 0.8010 | 52.1213 |
| 0.2735 | 6.4107 | 3000 | 0.8608 | 52.8648 |
| 0.2033 | 8.5476 | 4000 | 0.8979 | 51.6422 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1