whisper-small-sinhala-politics-5h

• Loss: 0.1543
• Wer: 28.6521

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: 8
• num_epochs: 8

Training results

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 4.4.1
• Tokenizers 0.22.1