Whisper Large v2 TR
This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 13 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2168
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: 128
- eval_batch_size: 128
- 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: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 328 | 0.1564 |
| 0.4016 | 2.0 | 656 | 0.1475 |
| 0.4016 | 3.0 | 984 | 0.1569 |
| 0.0623 | 4.0 | 1312 | 0.1748 |
| 0.0244 | 5.0 | 1640 | 0.1915 |
| 0.0244 | 6.0 | 1968 | 0.2168 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1