whisper-medium.en
This model is a fine-tuned version of crossdelenna/whisper-medium.en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0261
- Wer: 2.4421
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: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 800
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0446 | 0.3872 | 400 | 0.0520 | 4.2961 |
| 0.0387 | 0.7744 | 800 | 0.0261 | 2.4421 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1