add Lyra project under Compute category#30
Open
chrishyoroklee wants to merge 1 commit intoqualcomm:mainfrom
Open
add Lyra project under Compute category#30chrishyoroklee wants to merge 1 commit intoqualcomm:mainfrom
chrishyoroklee wants to merge 1 commit intoqualcomm:mainfrom
Conversation
Signed-off-by: Chris Hyorok Lee <hl3838@columbia.edu>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Project Outline:
Developed for the Snapdragon Multiverse Hackathon at Columbia University, the Lyra - Conversational Therapy Companion is a fully on-device AI voice assistant designed to provide accessible, privacy-first mental health support. Unlike cloud-based therapy chatbots, this system performs speech recognition, language modeling, and text-to-speech entirely locally. The application records user voice input, transcribes it using Whisper, generates a therapeutic response via a GGUF-based local LLM running with llama-cpp, and converts the response back into natural speech, ensuring that no sensitive data ever leaves the device.
Hardware Requirements:
Snapdragon PC (NPU-enabled)
Node.js 18+
Python 3.10+
FFmpeg (for audio processing)
Demo Output:
Real-time voice interaction powered by a fully local ASR → LLM → TTS pipeline, demonstrating secure, low-latency AI inference on consumer Snapdragon hardware with zero cloud dependency.