shangrilar's picture
whisper-small-ko-med
16bd8bf verified
metadata
base_model: shangrilar/techvillage_korean
tags:
  - generated_from_trainer
datasets:
  - audiofolder
model-index:
  - name: whisper-small-ko-med
    results: []

whisper-small-ko-med

This model is a fine-tuned version of shangrilar/techvillage_korean on the audiofolder 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: 32
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.1