whisper-medium-kor_eng_medium_ed_ev

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

• Loss: 0.0000
• Cer: 0.0

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0002	22.7273	1000	0.0002	50.0
0.0001	45.4545	2000	0.0001	0.0
0.0	68.1818	3000	0.0000	0.0
0.0	90.9091	4000	0.0000	0.0

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu126
• Datasets 3.5.0
• Tokenizers 0.21.1