livewhisper.py outputs psuedo-live sentence-by-sentence dictation to terminal. Using OpenAI's Whisper model, and sounddevice library to listen to microphone. Audio from mic is stored if it hits a volume & frequency threshold, then when silence is detected, it saves the audio to a temp file and sends it to Whisper.

Whisper realtime streaming for long speech-to-text transcription and translation

Real-time Speech To Text using Faster Whisper.