README.md

metadata

language:
  - ko
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - Bingsu/zeroth-korean
metrics:
  - wer
base_model: openai/whisper-small
model-index:
  - name: Whisper Small KR - BYoussef
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Bingsu/zeroth-korean
          type: Bingsu/zeroth-korean
        metrics:
          - type: wer
            value: 37.95
            name: Wer

Whisper Small KR - BYoussef

This model is a fine-tuned version of openai/whisper-small 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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.12.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2