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: 0.4660
- Wer: 14.5440
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 |
|---|---|---|---|---|
| 0.7649 | 0.55 | 30 | 0.4569 | 21.4116 |
| 0.3718 | 1.09 | 60 | 0.4107 | 14.9247 |
| 0.2053 | 1.64 | 90 | 0.3970 | 17.1451 |
| 0.1836 | 2.18 | 120 | 0.4242 | 14.0523 |
| 0.092 | 2.73 | 150 | 0.4120 | 14.4330 |
| 0.0648 | 3.27 | 180 | 0.4352 | 15.5115 |
| 0.0359 | 3.82 | 210 | 0.4290 | 15.0991 |
| 0.0205 | 4.36 | 240 | 0.4587 | 14.6392 |
| 0.0132 | 4.91 | 270 | 0.4660 | 14.5440 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0
- Downloads last month
- 3