Workshop: GPU-Powered Neural Audio
High-Performance Inference for Real-Time Sound Processing
Join our GPU AUDIO workshop where you'll dive into the exciting world of neural networks applied to real-time audio processing.
In this hands-on workshop, you’ll work with Neural Amp Modeler, an open-source project that uses deep learning techniques to replicate guitar amplifiers and pedals with state-of-the-art accuracy. You will learn how to port and scale the Neural Amp Modeler plugin to the GPU using GPU AUDIO technology stack.
With a focus on low-latency, parallel execution, and flexibility, you'll combine different neural building blocks to create high-performance audio models. Whether you're a neural network enthusiast or a DSP pro, this session will showcase how easily scalable models can be built with our specialized GPU neural building blocks.
Throughout the workshop, you'll work within a Jupyter environment, building and testing various versions of the Neural Amp Modeler.
After the session, you’ll gain access to the workshop’s codebase and environment, allowing you to set it up on your own machine and continue experimenting with real-time, low-latency audio processing.
Whether you're working with NVIDIA, AMD, or Mac (M-Silicon) platforms, this session serves as an exclusive sneak peek into our broader release of GPU-powered neural building blocks, unlocking the potential for real-time, scalable, low-latency audio processing like never before.
Alexander Prokopchuk
Co-founder & CTO
GPU Audio
Alexander Talashov
Co-founder & CEO
GPU Audio