Whisper Large v2 TR
This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1568
- Wer: 9.0189
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: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.1437 | 0.9997 | 1450 | 0.1550 | 9.9787 |
| 0.0766 | 2.0 | 2901 | 0.1470 | 9.3616 |
| 0.0371 | 2.9990 | 4350 | 0.1568 | 9.0189 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.17.1
- Tokenizers 0.19.1