Whisper Small Hre 4.2 - male and female voice - 600 steps, metric CER, skip_special_tokens False
This model is a fine-tuned version of openai/whisper-small on the Hre audio dataset 4 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0267
- Cer Ortho: 0.0669
- Cer: 1.8182
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer Ortho | Cer |
|---|---|---|---|---|---|
| 0.0302 | 2.48 | 600 | 0.0267 | 0.0669 | 1.8182 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 5