Whisper large v2 ap3 - Nuwan 6000
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5498
- Wer Ortho: 25.3509
- Wer: 24.8048
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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: constant_with_warmup
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.4024 | 0.2368 | 400 | 0.5385 | 27.1325 | 26.5465 |
| 0.3845 | 0.4737 | 800 | 0.5343 | 27.2490 | 26.6592 |
| 0.3835 | 0.7105 | 1200 | 0.5300 | 26.2049 | 25.6647 |
| 0.3466 | 0.9473 | 1600 | 0.5268 | 25.7677 | 25.2476 |
| 0.2737 | 1.1841 | 2000 | 0.5498 | 25.3509 | 24.8048 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1