Whisper Large_v2 RO CV17
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1703
- Wer: 11.1934
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: 8
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0921 | 1.7730 | 1000 | 0.1649 | 14.1850 |
| 0.0449 | 3.5461 | 2000 | 0.1538 | 14.7655 |
| 0.0205 | 5.3191 | 3000 | 0.1531 | 12.1407 |
| 0.0055 | 7.0922 | 4000 | 0.1638 | 11.6279 |
| 0.0012 | 8.8652 | 5000 | 0.1703 | 11.1934 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.19.1