RVC-Project/Retrieval-based-Voice-Conversion-WebUI

GANs

Open

#2,012 创建于 2024年4月23日

在 GitHub 查看
 (2 评论) (4 反应) (0 负责人)Python (18,427 star) (2,849 fork)batch import
enhancementhelp wanted

描述

I will make this short and quick for all of you to read. I think it would be a good idea if hifigan was switched with bigvgan for better fidelity and mel representation, or at the very least vocos. It would probably be a good idea to have this change included with RVC v3. @RVC-Boss

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
over 1 week
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
unclear
前置要求
Understanding of GANsFamiliarity with PyTorchKnowledge of RVC codebase
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
20
研究方向
Investigate the current implementation of HiFi GAN in the RVC project, likely in the models or modules directory. Compare it with BigVGAN and Vocos architectures. Determine the necessary changes to the training and inference code. Review any existing discussions or PRs related to model upgrades. Provide a clear proposal with estimated effort and expected improvements in fidelity.