<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
whisper-medium.en
This model is a fine-tuned version of crossdelenna/whisper-medium.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0942
- Wer: 5.3750
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- 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: 10
- training_steps: 452
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0512 | 0.27 | 150 | 0.2028 | 9.9969 |
| 0.1104 | 0.54 | 300 | 0.1616 | 8.9136 |
| 0.2051 | 0.81 | 450 | 0.0942 | 5.3750 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
