whisper-uyghur-medium3

• Cer: 0.1824
• Loss: 0.8845

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• 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

Framework versions

• PEFT 0.15.2
• Transformers 4.54.0
• Pytorch 2.7.1+cu126
• Datasets 3.5.1
• Tokenizers 0.21.2