Shuoyang Jasper Zheng

nn_terrain. Latent Terrain - Dissecting the Latent Space of Neural Audio Autoencoders

streamable-stable-audio-open. Streaming the autoencoder in Stable Audio Open 1.0 for realtime continuous inference in MaxMSP/PureData

ableton-sdk-mcp. Allowing LLM to operates Live by TypeScript commands, made via Ableton Extensions SDK

streamable-same-s. Streaming the SAME-S codec in Stable Audio 3 for realtime continuous inference

StyleGAN-Canvas. Implementation for "StyleGAN-Canvas: Augmenting StyleGAN3 for Real-Time Human-AI Co-Creation"

unsupervised-sketch-to-sound. Implementation of NIME24 paper: Building sketch-to-Sound mapping with unsupervised feature extraction and interactive machine learning

realtime-flask-model. Python

latent-terrain-pytorch. Reproducing experiments in the upcoming NIME26 paper "Latent Terrain: Adapting Neural Audio Autoencoders as Design Materials in NIME"

resonance-suppressor. Adaptive Resonance Suppressor

PyAudible. Sending and Receiving Data using Audible Sound