में बचाया:
ग्रंथसूची विवरण
मुख्य लेखकों: Lee, Sungho, Martínez-Ramírez, Marco, Liao, Wei-Hsiang, Uhlich, Stefan, Fabbro, Giorgio, Lee, Kyogu, Mitsufuji, Yuki
स्वरूप: Preprint
प्रकाशित: 2024
विषय:
ऑनलाइन पहुंच:https://arxiv.org/abs/2408.03204
टैग: टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
_version_ 1866917742284636160
author Lee, Sungho
Martínez-Ramírez, Marco
Liao, Wei-Hsiang
Uhlich, Stefan
Fabbro, Giorgio
Lee, Kyogu
Mitsufuji, Yuki
author_facet Lee, Sungho
Martínez-Ramírez, Marco
Liao, Wei-Hsiang
Uhlich, Stefan
Fabbro, Giorgio
Lee, Kyogu
Mitsufuji, Yuki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_03204
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch
Lee, Sungho
Martínez-Ramírez, Marco
Liao, Wei-Hsiang
Uhlich, Stefan
Fabbro, Giorgio
Lee, Kyogu
Mitsufuji, Yuki
Sound
Audio and Speech Processing
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.
title GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2408.03204