Whisper Large v2 TR
This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 16_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1739
- Wer: 9.1596
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: 8
- 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_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1425 | 1.0 | 5475 | 0.1734 | 10.7764 |
| 0.0714 | 2.0 | 10950 | 0.1627 | 9.6763 |
| 0.0283 | 3.0 | 16425 | 0.1739 | 9.1596 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 8