Whisper Large v2
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1401
- Wer Ortho: 0.1663
- Wer: 0.0689
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.1691 | 0.03 | 500 | 0.1776 | 0.2060 | 0.0941 |
| 0.1538 | 0.05 | 1000 | 0.1459 | 0.1743 | 0.0730 |
| 0.1522 | 0.08 | 1500 | 0.1401 | 0.1663 | 0.0689 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.1