hyangilam/whisper-large-v3-turbo-ko-0.0.3

Whisper Turbo Ko v0.0.3

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the zeroth_korean dataset. It achieves the following results on the evaluation set:

• Loss: 0.0642
• Cer: 2.1671

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: 16
• eval_batch_size: 16
• 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
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.1209	0.7184	1000	0.1275	4.0319
0.0348	1.4368	2000	0.0852	1.8569
0.0097	2.1552	3000	0.0741	2.4340
0.0082	2.8736	4000	0.0642	2.1671

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1