Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper Medium - Zakryah
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2774
- Wer: 53.6224
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: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.571 | 0.3299 | 1000 | 0.5218 | 40.5852 |
| 0.3314 | 0.6598 | 2000 | 0.2860 | 57.7835 |
| 0.2971 | 0.9898 | 3000 | 0.2791 | 54.2644 |
| 0.2622 | 1.3197 | 4000 | 0.2774 | 53.6224 |
Framework versions
- PEFT 0.14.1.dev0
- Transformers 4.50.0.dev0
- Pytorch 2.6.0+cu126
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Zakryah/whisper-medium2
Base model
openai/whisper-medium