Real-time Censorship for Misophonia
Goals:
Train an AI agent that can recognize an audio trigger.(85% accuracy but needs work still) ✅
Create a buffer system to hold audio data for a delay before playing it. (some bugs still) ✅
Allow the user to upload audio or video files to be analyzed and played back. ✅
Create an easy-to-use UI system.✅
Allow the user to feed in live microphone audio or record live audio for later playback. (not yet finished)❌
Integrate web access for the processing of live audio from the web. (third-party updates needed)❌
Add in censorship for visual triggers (may or may not happen)❌
Feedback
you can share your triggers annonamysly below and leave sugestions so I can add a filter to help you and improve the usability of this application.