README.md

metadata

language:
  - bn
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Bengali
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0 bn
          type: mozilla-foundation/common_voice_11_0
          config: bn
          split: test
          args: bn
        metrics:
          - name: Wer
            type: wer
            value: 18.22

Whisper Small Bengali

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 bn dataset. It achieves the following results on the evaluation set:

• Loss: 0.1638
• Wer: 18.22