Retrieval-based-Voice-Conversion-WebUI

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

Does rvc support training with cpu?

18

Hello, may I ask if RVC supports training with CPU? Because I don't have a separate graphics card, and I encountered an error in the second step of training, which...

c469591

More dynamic volume range in future generations?

2

When pre-processing the wavs, they are all normalized to keep the dataset even and consistent. This makes sense to me as a method to ensure data processed is relatively similar,...

kalomaze

modify log to like this `====> Epoch: 204 [2023-05-12 21:14:24] | (0:01:10.741618)`

Xerxes-2

[Feature request] Automatic batch processing of long files on harvest for limited RAM machines

4

A common complaint from Google Colab users is harvest being unusable without manually splitting their song into parts. I wonder if an argument in the command to run python infer-web.py...

kalomaze

[Feature Request] Adding Timestamp and Epoch Time Spent to Console Output

2

## Issue Description: Currently, when running the training script, the console output doesn't provide any information about the timestamp or the time spent for each epoch. This information would be...

Xerxes-2

AMD Support - Segmentation Fault

40

System: ``` Ubuntu 22.04 LTS Intel i5-12600k 32GB DDR4 AMD Radeon RX 6650 XT ``` Manually installed PyTorch 2.0.1 for rocm. Then installed requirements from requirements.txt. webui boots up without...

Chilluminati91

[Bug] RuntimeError: CUDA error: an illegal instruction was encountered

6

Using an Ubuntu system, 2x3060 (12g ea) and the latest version of RVC, commit c4a1810 During training, after a few epochs complete, a CUDA error is thrown: ``` INFO:user-test-3:====> Epoch:...

mr-segfault

Hi, I was wondering if it would be possible to support the voice separation function of pyanno.audio in future versions? This package would make file organization much easier, especially when...

c469591

启动后没有声音，扬声器音量爆满

7

显卡1660s [logs.zip](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/files/11452178/logs.zip)

zlh543935243

Standard for most of recorded music is 44khz instead of 40khz

2

I've been told contentvec hubert was trained at 44khz, but there are 3 options in RVC for 40khz, 48khz, and 32khz. This confuses me, as the standard for most recorded...

kalomaze