We present GRAFX, an open-source library designed for handling audio processing graphs in PyTorch. Along with various library functionalities, we describe technical details on the efficient parallel computation of input graphs, signals, and processor parameters in GPU. Then, we show its example use under a music mixing scenario, where parameters of every differentiable processor in a large graph are optimized via gradient descent. The code is available at https://github.com/sh-lee97/grafx.

翻译：本文介绍GRAFX——一个专为PyTorch音频处理图设计的开源库。在阐述各项库功能的同时，我们详细说明了在GPU上高效并行计算输入图、信号及处理器参数的技术细节。随后通过音乐混音场景下的应用示例，展示了如何通过梯度下降优化大型图中所有可微分处理器的参数。代码发布于https://github.com/sh-lee97/grafx。