Retrieval-based-Voice-Conversion-WebUI

Retrieval-based-Voice-Conversion-WebUI copied to clipboard

 Hi, I'm encountering a ConnectionResetError [WinError 10054] whenever I attempt to convert a voice using the rvc beta 0717, RVC1006Nvidia, and Mangio-RVC-v23.7.0 releases. same error is being displayed in...

jasonmomos

#### Description When setting the device type to ASIO in `gui_v1.py`, both input and output audio channels experience stuttering and the sound is not continuous. It appears that the `GUI.audio_callback`...

wellcoming

doesn't want to use a video card

2

I downloaded the version for Nvidia GPU I have a 1080ti. But the load goes only to the processor and the video card is loaded at 0.00

RemMajiTensh1

训练出来效果差

1

为什么自己训练出来的模型效果那么差呢，我用20分钟的音频训练，虽然改变了声音但是跟原先的音色查不了多少啊，是因为微调过度了吗

holylong

Seeking Help: Issue Installing fairseq as a Python Newbie

3

The problem arises during the wheel building process for fairseq. As a complete Python novice, I’m feeling a bit lost. Here are the details of my setup: Python version: 3.10.11...

AkaitsukiBrunestud

After updating it to the latest, I've been getting this error

3

``` Traceback (most recent call last): File "K:\AI\10\Retrieval-based-Voice-Conversion-WebUI 2\gui_v1.py", line 87, in import FreeSimpleGUI as sg ModuleNotFoundError: No module named 'FreeSimpleGUI' Press any key to continue . . . ```...

Jeet-Srimani

WinError 3 Error

1

I don't undertstand why I am receiving this error, any help would be greatly appreciated! Process Process-1: Traceback (most recent call last): File "multiprocessing\process.py", line 315, in _bootstrap File "multiprocessing\process.py",...

JustCann

How to get or create a json file after pht convertion to onnx? I took a look in other voice jsons, they look all different, so I cant copy one...

cushycrux

Crash with AttributeError: 'tuple' object has no attribute 'split' when trying to convert to onnx

1

Hi guys, I hope someone can help. installed the large all-in-one windows repo. When I try to convert pth to onnx the app traces back. go_web.bat is starting well. When...

cushycrux

关于gui_v1.py使用ASIO驱动的踩坑反馈

1

遇到的问题 1. 如果先选择了使用设备采样率，然后切换设备类型，切换后界面仍选中“使用设备采样率”，但是实际上代码逻辑会重置回“使用模型采样率” 2. 使用ASIO的时候，大部分模型的采样率都是40000，而使用asio驱动好像必须要输入采样率和asio的采样率一致，故ASIO模式下，使用模型采样率大概率失败，页面直接消失； 3. ASIO的采样率是通过default samplerate来进行获取的，但是很多独立声卡的default samplerate值与实际工作运行的值不一样，导致使用get_device_samplerate获取的asio声卡默认采样率实际上并不是设备的工作采样率而导致失败 4. 使用ASIO设备会爆音，即使把buffer调整的很大；【目前不知道怎么优化解决】 5. ASIO的输入和输出设备好像需要完全一样，如果不一样会报错说invalid pair 我的临时爬坑 1. 切换到ASIO后手动选择一下模型采样率再手动选回设备采样率 2. 在代码里把get_device_samplerate的return直接写死成我的声卡工作采样率 可参考的优化： 1. 切换到ASIO模式后，让用户自己选他的声卡设备采样率 2. 切换到ASIO模式后，前端检测输入设备和输出设备是否对的上 以上是我踩坑发现并临时解决的的一些问题，让gui_v1能在voicemeeter+steinberg声卡上跑ASIO模式，但仍然被爆音问题所困，目前暂时未能跑起来，关于问题归因可能不对，瞎猫子撞上了，如有错误肯请指点！ 最后感谢项目主如此精彩的Work！如果有空可以抽空修复一下，再次感谢！

SimpleRealDT