Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
whisper-uyghur-medium3
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Cer: 0.1824
- Loss: 0.8845
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Cer | Validation Loss |
|---|---|---|---|---|
| 2.7137 | 0.6667 | 150 | 0.3007 | 1.8328 |
| 2.037 | 1.3333 | 300 | 0.2714 | 1.0958 |
| 1.8441 | 2.0 | 450 | 0.2380 | 1.0061 |
| 1.7696 | 2.6667 | 600 | 0.2201 | 0.9485 |
| 1.702 | 3.3333 | 750 | 0.2048 | 0.9171 |
| 1.7269 | 4.0 | 900 | 0.1818 | 0.8955 |
| 1.6546 | 4.6667 | 1050 | 0.1824 | 0.8845 |
Framework versions
- PEFT 0.15.2
- Transformers 4.54.0
- Pytorch 2.7.1+cu126
- Datasets 3.5.1
- Tokenizers 0.21.2
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for 21f3002101/whisper-uyghur-medium3
Base model
openai/whisper-medium