Whisper Large v2 TR
This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1555
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4239 | 1.0 | 726 | 0.1516 |
| 0.0998 | 2.0 | 1452 | 0.1469 |
| 0.0399 | 3.0 | 2178 | 0.1555 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1