Model weights for DiffRoll

Name: Model weights for DiffRoll
Creator: Shusuke Takahashi; Singapore University of Technology and Design and Sony Group Corporation; Singapore University of Technology and Design; Sony Group Corporation
Published: 2022-10-17T00:00:00+08:00

Zenodo2022-10-17 更新2026-04-07 收录

音乐自动转录

扩散模型

数据链接：

https://zenodo.org/record/7246522 数据链接链接失效反馈

官方服务：

资源简介：

This repository contains the pre-trained model weights for DiffRoll proposed in the paper DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability by Sony.<br> More information about DiffRoll including its Demo is available in https://sony.github.io/DiffRoll/.

提供机构：

Shusuke Takahashi; Singapore University of Technology and Design and Sony Group Corporation; Singapore University of Technology and Design; Sony Group Corporation

创建时间：

2022-10-17