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: 0.2887
- Wer: 9.9198
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 |
|---|---|---|---|---|
| 0.5542 | 0.49 | 30 | 0.2941 | 13.0145 |
| 0.2716 | 0.98 | 60 | 0.2636 | 12.2538 |
| 0.1438 | 1.48 | 90 | 0.2603 | 11.0868 |
| 0.1345 | 1.97 | 120 | 0.2502 | 12.1809 |
| 0.0619 | 2.46 | 150 | 0.2587 | 12.3476 |
| 0.0552 | 2.95 | 180 | 0.2634 | 10.3366 |
| 0.0293 | 3.44 | 210 | 0.2722 | 10.0240 |
| 0.0206 | 3.93 | 240 | 0.2670 | 9.7739 |
| 0.0108 | 4.43 | 270 | 0.2838 | 9.8364 |
| 0.008 | 4.92 | 300 | 0.2887 | 9.9198 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0
- Downloads last month
- 3