README.md

metadata

language:
  - ko
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - generated_from_trainer
datasets:
  - vts_sample_data
metrics:
  - wer
model-index:
  - name: VTS_Model by Edgar
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: vts_sample_data
          type: vts_sample_data
          args: 'config: ko, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 5.263157894736842

VTS_Model by Edgar

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

• Loss: 1.1127
• Wer: 5.2632

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: 0.001
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• training_steps: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.7293	0.1667	1	1.1127	5.2632

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1