README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - en-asr-leaderboard
  - generated_from_trainer
datasets:
  - mn367/radio-test-dataset
metrics:
  - wer
model-index:
  - name: Whisper Medium En
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Radio dataset
          type: mn367/radio-test-dataset
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 30.971856370442257

Whisper Medium En

Framework versions

• Transformers 4.25.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.7.0
• Tokenizers 0.13.2