openai/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: 0.1534
- Wer: 145.6786
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: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0799 | 2.03 | 500 | 0.1010 | 28.1322 |
| 0.0239 | 5.01 | 1000 | 0.1388 | 161.0139 |
| 0.0066 | 7.03 | 1500 | 0.1221 | 99.3747 |
| 0.0007 | 10.01 | 2000 | 0.1295 | 250.8822 |
| 0.0007 | 12.04 | 2500 | 0.1423 | 77.2203 |
| 0.0003 | 15.02 | 3000 | 0.1480 | 149.4380 |
| 0.0001 | 17.05 | 3500 | 0.1518 | 141.5842 |
| 0.0001 | 20.02 | 4000 | 0.1534 | 145.6786 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2