On-Device Offline Voice Assistant with Whisper Tiny & Quantized LLM
100% offline, privacy-first smart home assistant running quantized Whisper ASR and TinyLlama on a local single-board computer.
Customized to Your Project Requirements
All engineering projects are custom fabricated to match your specific IEEE publication standards, academic department guidelines, and selected hardware/sensor stack. Request a custom quote to receive an itemized proposal, timeline, and deliverables list.
Project Technical Overview
Requires zero cloud connectivity, safeguarding household privacy. Uses an optimized onnxruntime Whisper Tiny model to transcribe voice commands into text in under 200ms, parses home automation intents with a 4-bit quantized local LLM, and triggers local relays/lights.
Read the foundational IEEE conference research paper, citations, and algorithmic architecture for this project.