Problem Description

I am looking to create an MVP that can use whisper to simulate real-time voice to text transcription + understand some basic voice commands. I understand Whisper is not yet real time but wonder if we can try to simulate real-time transcription in a local environment.

Here is an example: https://github.com/davabase/whisper_real_time

Acceptance Criteria

An OSX tool that runs locally that uses OpenAI Whisper model to transcribe audio, in simulated real-time. It allows for the user to say a voice command, "Copy Text" to copy the text to the clipboard and "Paste Text" to paste the text.