HARP - Bringing Deep Learning to the DAW with Hosted, Asynchronous, Remote Processing

Hugo Flores Garcia, Patrick O'Reilly, Bryan Pardo, Christodoulos Benetatos, Zhiyao Duan

Source Code and Plugin

This work supported by NSF Award Number 2222369

HARP is an ARA plug-in that allows for hosted, asynchronous, remote processing of audio with deep learning models. HARP works by routing audio from a digital audio workstation (DAW) through Gradio endpoints. Because Gradio apps can be hosted locally or in the cloud (e.g., HuggingFace Spaces), HARP lets users of Digital Audio Workstations (e.g. Reaper) access large state-of-the-art models in the cloud, without breaking their within-DAW workflow.

[pdf]H. Flores Garcia, P. O’Reilly, A. Aguilar, B. Pardo, C. Benetatos, and Z. Duan, “HARP: Bringing Deep Learning to the DAW with Hosted, Asynchronous, Remote Processing,” in NeurIPS Workshop on Machine Learning for Creativity and Design, 2023.