README.md

metadata

language:
  - ko
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - Bingsu/zeroth-korean
model-index:
  - name: Whisper Fine-tuning Test
    results: []

Whisper Fine-tuning Test

This model is a fine-tuned version of openai/whisper-large-v3 on the Zeroth-Korean dataset.

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.39.0
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.15.2