RuidaJiang/whisper-tiny_to_korean_accent

Whisper tiny Korean

This model is a fine-tuned version of openai/whisper-tiny on the Korean English dataset. It achieves the following results on the evaluation set:

• Loss: 0.2028
• Wer: 10.5854
• Vowel Wer: 40.4444
• Vowel A Wer: 11.5753

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: 2
• eval_batch_size: 1
• 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: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Vowel Wer	Vowel A Wer
0.1753	1.0173	1000	0.2164	10.3902	40.6667	10.2698
0.0743	2.0346	2000	0.2028	10.5854	40.4444	11.5753

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.4.0
• Tokenizers 0.21.0