whisper-small-pulaar-kallaama
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: 3.3463
- Wer: 65.3061
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: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 10.7473 | 2.7778 | 25 | 7.4316 | 100.0 |
| 3.4657 | 5.5556 | 50 | 3.3463 | 65.3061 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1