whisper-medium-ga2en-v5.3.1-1
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2003
- Bleu: 5.336
- Gen Len: 17.3355
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|
| 0.2183 | 1.0 | 500 | 0.2026 | 7.5494 | 17.4175 |
| 0.2128 | 2.0 | 1000 | 0.2003 | 5.336 | 17.3355 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
