Retrieval-based-Voice-Conversion-WebUI
Retrieval-based-Voice-Conversion-WebUI copied to clipboard
Easily train a good VC model with voice data <= 10 mins!
小白一枚,要完成设计项目,希望大佬们不吝赐教,讲解一下模型训练和推理的技术路线,有偿,可加微信QQ
Hello, Is it possible to average two or more trained models together? I can train a model that has 2 people in it, effectively doing the same thing, but I...
# PR type - Document fix # Description - 更正README中使用poetry安装依赖时给出的错误文件名 # Screenshot - N/A
大佬们,这个问题骚扰我好久了,嗷嗷! 我有一张Nvidia的显卡,但是只有2G的显存,理论上是不能用来训练的。 升级显卡也做不到,因为是笔记本电脑,显卡是锡焊在主板上的。 更换电脑也做不到,因为过去装了很多音乐制作的软件,都自定义配置好了,没办法重新安装。 使用Colab也做不到,因为Colab是基于Linux系统的,而我想在本地的Windows系统上进行训练,借此来学习RVC的运作。而且Colab最近在严打语音方面的DeepFake,甚至连相关的Gradio界面也会被封禁。 嗷嗷! 所以,我希望大佬们可以指点迷津,如何用CPU和内存来进行训练? 我知道会很慢,但是我只需要训练一个周杰伦的模型就够了,而且我可以在晚上睡觉的时候开机训练,训练几个星期都可以接受。 **我的系统是:** Intel i7 4th Gen Quadcore CPU 12GB RAM Windows 7 Professional 64 Bit Nividia GeForce GTX 660M 请问是否在环境里安装一个CPU版本的PyTorch就足够了? 如果不安装directml相关的依赖,比如onnxruntime-directml之类的,RVC能不能用来训练呢?因为我的系统是Windows 7,无法安装DirectX 12,所以系统不支持directml。...
Update the Gradio library to the latest possible version. I checked it, it all seems to work without any problems.
Hello, Once I trained a model and obtained a "modelOfaVoice.pth", Where can I go to use it in an effiscient way to obtain very nice voices that looks like human?...
Is there any way to get zluda to work with RVC? thanks
Hi There, I made download and Model Inference works good, but The Train Section to clone my voice isn't generating the archive .pth to anyplace, RVC just generated a folder...
I've been completed training my model locally, but when I check the logs folder, I can't find the index file of the model.  ...
一键训练后没有index文件,点击train feature index只会在output information那里快速闪一下,然后就变回原样并且任然没有index输出。版本为最新版本,训练选项均为默认选项,依赖项全部安装,显卡是rtx3050。configs文件夹中的config文件也删过一次了也没用。