a custom comfyui node for OpenVoice to voice cloning and tts
make sure ffmpeg
is worked in your commandline
for Linux
apt update
apt install ffmpeg
for Windows,you can install ffmpeg
by WingetUI automatically
Download the checkpoint from here and extract it to the ComfyUI-OpenVoice
folder.
git clone https://github.com/AIFSH/ComfyUI-OpenVoice.git
cd ComfyUI-OpenVoice
pip install -r requirements.txt
python -m unidic download
tts weights
will be downloaded from huggingface automatically! if you in china,make sure your internet attach the huggingface
or if you still struggle with huggingface, you may try follow hf-mirror to config your env.
Could not load library libcudnn_cnn_infer.so.8. Error: /usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8: undefined symbol: _ZN11nvrtcHelper4loadEb, version libcudnn_ops_infer.so.8
Please make sure libcudnn_cnn_infer.so.8 is in your library path!
fix by
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/miniconda3/lib/python3.10/site-packages/torch/lib
issueを英語で書く必要はありません。
------------------- ERROR DETAILS ------------------------
arguments:
[ifs] no such file or directory: /usr/local/miniconda3/lib/python3.10/site-packages/unidic/dicdir/mecabrc
----------------------------------------------------------
fix by
cp -r /usr/local/miniconda3/lib/python3.10/site-packages/unidic_lite/dicdir /usr/local/miniconda3/lib/python3.10/site-packages/unidic/