openai/whisper-large
This model is a fine-tuned version of openai/whisper-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6750
- Wer: 16.9811
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1978 | 2.01 | 100 | 0.5474 | 21.0692 |
| 0.0087 | 4.02 | 200 | 0.6202 | 19.4969 |
| 0.0029 | 6.04 | 300 | 0.6264 | 18.2390 |
| 0.0003 | 8.05 | 400 | 0.6659 | 17.1908 |
| 0.0002 | 10.06 | 500 | 0.6750 | 16.9811 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2