aldisa546/whisper-large-ratu-ft

whisper-large-training

This model is a fine-tuned version of openai/whisper-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2921
• Wer: 0.1378

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.002	6.1200	5000	0.2845	0.1337

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.2