Retrieval-based-Voice-Conversion-WebUI

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

Feature File Path and Database File paths not being written after training

16

Using current version of RVC (pulled the latest to verify just before writing this report), When Training, it generates the weights but does not generate the feature file or database...

mr-segfault

Error during training, FileNotFound

5

When trying to train using the One-click training, I get the following error: ``` C:\Users\LXC PC\Desktop\RVC\venv\Scripts>activate (venv) C:\Users\LXC PC\Desktop\RVC\venv\Scripts>cd C:\Users\LXC PC\Desktop\RVC\venv\Scripts\RVC-beta (venv) C:\Users\LXC PC\Desktop\RVC\venv\Scripts\RVC-beta>go-web.bat (venv) C:\Users\LXC PC\Desktop\RVC\venv\Scripts\RVC-beta>runtime\python.exe infer-web.py --pycmd runtime\python.exe...

ThrowawayAccount01

无法创建索引

7

`ValueError: need at least one array to concatenate` ``` /root/miniconda3/envs/rvc/lib/python3.10/site-packages/torch/optim/lr_scheduler.py:138: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order:...

koaqiu

MacOS Apple M1 Pro faiss-cpu==1.7.0 报错

9

修改requirements.txt中的 ``` faiss-cpu==1.7.0; sys_platform == "darwin" ``` ``` faiss-cpu==1.7.2; sys_platform == "darwin" ``` 则不会报错，顺利安装成功。 python版本3.10 原安装错误信息 ```bash pip3 install faiss-cpu==1.7.0 --no-cache-dir Collecting faiss-cpu==1.7.0 Downloading faiss-cpu-1.7.0.tar.gz (34 kB) Preparing metadata (setup.py)...

ourines

Gradio: training Pause/Resume support

2

With the Colab free plan, the GPU are stopped after a few hours of use. It will be available again after 12 hours. I would like a feature to pause...

kagekiyo7

Female to Male Voice Help

2

Thank you for this interesting repository! I was hoping you could give me some tips. I've implemented the Colab code, training with around 9 minutes of one spoken male voice...

mdyfong

训练失败，The server socket has failed to bind to [kodachi]:51545 (system error: 10013

2

启动web页面后，只改了实验名和训练文件夹路径，然后点击一键训练。后面报错提示端口占用，已经查过了，并没有程序占用51545端口。 系统是windows11，kodachi是我电脑名字 下面是log INFO:qi:{'train': {'log_interval': 200, 'seed': 1234, 'epochs': 20000, 'learning_rate': 0.0001, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 3, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 12800, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel':...

KodachiGitHub

Can we please have release notes in english? It is very hard for implementors to detect/track breaking changes, etc.

3

We should also try to use M.m.p versioning (where M is major, m is minor and p is patch: eg. 2.4.3) which makes this more obvious just from the version...

sgsavu

I have two systems training on identical datasets System A has 4 x NVIDIA RTX A5000 (24GB VRAM per GPU), and a batch size of 12 per GPU. System B...

scf4

开始转换声音会闪退

5

 使用群内提供的模型后出现这个错误 请问这要如何解决 谢谢作者大大们

kirari3