Finetuning_Whisper_Ko

This model is a fine-tuned version of openai/whisper-base on the 저음질 전화음성 데이터 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4382
• Cer: 16.7767

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: 8
• seed: 42
• 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.6311	0.5010	1000	0.6099	27.3330
0.495	1.0020	2000	0.5025	19.3769
0.4176	1.5030	3000	0.4573	17.4759
0.3789	2.0040	4000	0.4382	16.7767

Framework versions

• Transformers 4.52.0.dev0
• Pytorch 2.5.1+cu121
• Datasets 3.6.0
• Tokenizers 0.21.1