whisper-tiny-pulaar-kallaama
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: 1.4152
- Wer: 41.9355
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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 |
|---|---|---|---|---|
| 0.8144 | 11.1111 | 100 | 1.2741 | 41.9355 |
| 0.4744 | 22.2222 | 200 | 1.6830 | 77.4194 |
| 0.3982 | 33.3333 | 300 | 1.4156 | 77.4194 |
| 0.3752 | 44.4444 | 400 | 1.4065 | 41.9355 |
| 0.3611 | 55.5556 | 500 | 1.4152 | 41.9355 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1