Whisper Large V2
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: 0.4332
- Wer: 16.4588
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6839 | 0.71 | 30 | 0.4569 | 19.2143 |
| 0.2718 | 1.43 | 60 | 0.3925 | 17.6876 |
| 0.1785 | 2.14 | 90 | 0.3953 | 15.2113 |
| 0.0779 | 2.86 | 120 | 0.4030 | 17.3338 |
| 0.0449 | 3.57 | 150 | 0.4335 | 20.2942 |
| 0.0229 | 4.29 | 180 | 0.4239 | 14.4852 |
| 0.0114 | 5.0 | 210 | 0.4332 | 16.4588 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0
- Downloads last month
- 3