search

tobiashuttinger / openai-whisper-realtime

A quick experiment to achieve almost realtime transcription using Whisper.
MIT License
185 stars 28 forks source link

Inspiration from Dragonfly #2

Closed LexiconCode closed 1 year ago

LexiconCode commented 2 years ago

Take a look at the following: https://github.com/dictation-toolbox/dragonfly/blob/a2b8f8e8ed1182465b831205b9804323beea112a/dragonfly/engines/backend_kaldi/audio.py

It uses webrtcvad to filter and segment audio with voice activity detection.