lower01

Hello, have you implemented a demo that only applies the pre-trained model without training for VC?

I also don't know how to test with another input audio

> I have already gave this project a star.... Can you help me, please? Hello brother, like you, I constructed the graph data myself and then output the similarity based...

Hello brother, like you, I constructed the graph data myself and then output the similarity based on prediction. Even for the same data, it is around 0.5, which I can’t...

> 理论上你把model_dir 这里 设置为你下载的whisper路径就可以了 那估计没有这么简单，CPU版和GPU版教程我都试过很多次whisper-large-v3了，不管是自己预先下载的还是自动下载的，都无法启动服务，cpu版我试sensevoice-small和paraformer-large都可以，GPU版示例的paraformer-large可以，但是多次尝试sensevoice-small和whisper-large-v3都不行，也都是从modelscope中下载的，应该是项目中提供的处理脚本并没有支持whisper

原因都能想到是这个，主要是想知道有没有其它GPU版能部署whisper-large-v3的方法呢，项目文档教程里面的中文离线GPU版部署里面不会只能用paraformer吧 ------------------ 原始邮件 ------------------ 发件人: ***@***.***>; 发送时间: 2025年3月20日(星期四) 下午4:53 收件人: ***@***.***>; 抄送: ***@***.***>; ***@***.***>; 主题: Re: [modelscope/FunASR] 服务器部署问题，求大佬帮忙 (Issue #2423) 因为GPU版会自动导出torchscript，但whisper-large-v3并不支持这么做 — Reply to this email directly, view it on GitHub, or...