search

tsurumeso / vocal-remover

Vocal Remover using Deep Neural Networks
MIT License
1.55k stars 222 forks source link

Cannot use GPU in vocal removing #83

Open Nova-Dvorak opened 3 years ago

Nova-Dvorak commented 3 years ago

I've added the --gpu parameter, but it seemed that my GPU just didn't work, while my CPU usage became 100%. I use i5-9400F with an RTX2060. Here is the list of my installed libraries: Package Version

appdirs 1.4.4 audioread 2.1.9 certifi 2020.12.5 cffi 1.14.5 chardet 3.0.4 decorator 4.4.2 idna 2.10 joblib 1.0.1 librosa 0.8.0 llvmlite 0.36.0 numba 0.53.0 numpy 1.20.1 opencv-python 4.5.1.48 packaging 20.9 pip 20.3.1 pooch 1.3.0 pycparser 2.20 pylightxl 1.51 pyparsing 2.4.7 requests 2.25.0 resampy 0.2.2 scikit-learn 0.24.1 scipy 1.6.1 setuptools 49.2.1 six 1.15.0 SoundFile 0.10.3.post1 threadpoolctl 2.1.0 torch 1.8.0 tqdm 4.59.0 typing-extensions 3.7.4.3 urllib3 1.26.2

tsurumeso commented 3 years ago

Please follow the instructions below to install the GPU version of PyTorch. https://pytorch.org/get-started/locally/