Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
whisper-uyghur-medium4
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: 0.2150
- Loss: 0.9740
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Cer | Validation Loss |
|---|---|---|---|---|
| 2.9729 | 0.4444 | 100 | 0.4515 | 2.1406 |
| 2.382 | 0.8889 | 200 | 0.2038 | 1.4717 |
| 1.9727 | 1.3333 | 300 | 0.2243 | 1.0942 |
| 1.8029 | 1.7778 | 400 | 0.2354 | 1.0281 |
| 1.7587 | 2.2222 | 500 | 0.2214 | 0.9953 |
| 1.7162 | 2.6667 | 600 | 0.2150 | 0.9740 |
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
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for 21f3002101/whisper-uyghur-medium4
Base model
openai/whisper-medium