README.md

metadata

library_name: transformers
language:
  - ko
license: mit
base_model: imTak/whisper_large_v3_ko_ft_ft
tags:
  - generated_from_trainer
datasets:
  - imTak/korean-speak-Develop
metrics:
  - wer
model-index:
  - name: Whisper large v3 turbo Korean-Develop
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Develop
          type: imTak/korean-speak-Develop
          args: 'config: ko, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 16.64530599166934

Whisper large v3 turbo Korean-Develop

This model is a fine-tuned version of imTak/whisper_large_v3_ko_ft_ft on the Develop dataset. It achieves the following results on the evaluation set:

• Loss: 0.2410
• Wer: 16.6453

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2119	1.9455	500	0.2721	22.6690
0.0714	3.8911	1000	0.2542	19.9135
0.0145	5.8366	1500	0.2417	18.5037
0.0018	7.7821	2000	0.2410	16.6453

Framework versions

• Transformers 4.45.0
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3