macOS M1 webUI一键训练时error

[nawoobobo]

File "/opt/anaconda3/envs/RVC/lib/python3.11/site-packages/ffmpeg/_run.py", line 325, in run raise Error('ffmpeg', out, err) ffmpeg._run.Error: ffmpeg error (see stderr output for detail)

File "/Users/rw/Downloads/RVC/infer/lib/audio.py", line 43, in load_audio raise RuntimeError(f"Failed to load audio: {e}") RuntimeError: Failed to load audio: ffmpeg error (see stderr output for detail)

Traceback (most recent call last): File "/Users/rw/Downloads/RVC/infer/modules/train/extract/extract_f0_rmvpe_dml.py", line 19, in import torch_directml ModuleNotFoundError: No module named ‘torch_directml'

File "/Users/rw/Downloads/RVC/infer-web.py", line 756, in train1key click_train( File "/Users/rw/Downloads/RVC/infer-web.py", line 497, in click_train & set([name.split(".")[0] for name in os.listdir(f0nsf_dir)]) ^^^^^^^^^^^^^^^^^^^^^ FileNotFoundError: [Errno 2] No such file or directory: '/Users/rw/Downloads/RVC/logs/mi-test/2b-f0nsf’

上面是我出现的几个error message 已经尝试好几次重新安装ffmpeg，但没有效果；

我的硬件mac mini M1，内存8G，系统版本macOS 14.2 软件官网下载anaconda，RVC整合包(/Users/rw/Downloads/RVC) 训练集(/Users/rw/Downloads/mi-test)

There are error message. I have tried to install ffmpeg, uninstall ffmpeg and install ffmpeg many times. However, it didn’t work. Download anaconda from official website.

# 安装ffmpeg
cd Downloads
cd RVC
brew install ffmpeg

# 创建环境、安装依赖
conda create -n RVC python=3.11
conda activate RVC
pip3 install -r requirements.txt
pip3 uninstall torch torchaudio
pip3 install --pre torch torchaudio --index-url https://download.pytorch.org/whl/nightly/cpu

# 安装aria2
brew install aria2 

# 安装assets预模型
cd assets
pip3 install huggingface_hub
huggingface-cli download --resume-download lj1995/VoiceConversionWebUI/hubert --local-dir-use-symlinks False 
huggingface-cli download --resume-download lj1995/VoiceConversionWebUI/pretrained --local-dir-use-symlinks False 
huggingface-cli download --resume-download lj1995/VoiceConversionWebUI/uvr5_weights --local-dir-use-symlinks False 
huggingface-cli download --resume-download lj1995/VoiceConversionWebUI/pretrained_v2 --local-dir-use-symlinks False 

# 修复python 3.11 fairseq bug
pip install git+https://github.com/One-sixth/fairseq.git

# 执行webUI(使用python 3.11)
sh ./run.sh

[fumiama]

看报错

ModuleNotFoundError: No module named ‘torch_directml'

你代码调用了dml，但是MacOS M1无论如何用不到，所以考虑你下错了整合包。有能力的话建议直接使用dev版本。整合包都是给Windows用户准备的。

[nawoobobo]

发现是在我webUI界面选到gpu的模型所以报错，现在点rmvpe已解决 I found that I clicked on the gpu option and it has been solved now.