Whisper Small Ha adam_w v4 - Eldad Akhaumere
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:
- Loss: 2.2150
- Wer Ortho: 81.0547
- Wer: 78.8657
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: 5e-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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 15.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0995 | 3.1847 | 500 | 1.7910 | 90.4297 | 88.1778 |
| 0.0468 | 6.3694 | 1000 | 1.9594 | 82.8320 | 81.1458 |
| 0.0394 | 9.5541 | 1500 | 2.0776 | 89.8438 | 87.7563 |
| 0.0314 | 12.7389 | 2000 | 2.2150 | 81.0547 | 78.8657 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1