axeldelafosse/stemgen

Intel GPU accelleration

MemeGLS opened this issue · 0 comments

Hello, I'm looking for a way to use the GPU acceleration with an Intel GPU. I was able to use it with demucs-gui https://github.com/CarlGao4/Demucs-Gui/releases, but unfortunately I wasn't able to do it via Stemgen.

I'm currently on Windows 11 with an Intel Arc Graphic and this is what happen when I run the command:

C:\Users\emiso\stemgen>python stemgen.py "C:\Users\emiso\stemgen\sources\Kavinsky - Nightcall.flac" -d cuda
Using GPU for processing.
Output dir already exists.
Working dir created.
Done.
Extracting bit depth...
bits_per_sample=16
Done.
Extracting sample rate...
sample_rate=44100
Done.
Extracting cover...
ffmpeg version N-117094-g2bf588f273-20240921 Copyright (c) 2000-2024 the FFmpeg developers
built with gcc 14.2.0 (crosstool-NG 1.26.0.106_ed12fa6)
configuration: --prefix=/ffbuild/prefix --pkg-config-flags=--static --pkg-config=pkg-config --cross-prefix=x86_64-w64-mingw32- --arch=x86_64 --target-os=mingw32 --enable-gpl --enable-version3 --disable-debug --enable-shared --disable-static --disable-w32threads --enable-pthreads --enable-iconv --enable-zlib --enable-libfreetype --enable-libfribidi --enable-gmp --enable-libxml2 --enable-lzma --enable-fontconfig --enable-libharfbuzz --enable-libvorbis --enable-opencl --disable-libpulse --enable-libvmaf --disable-libxcb --disable-xlib --enable-amf --enable-libaom --enable-libaribb24 --enable-avisynth --enable-chromaprint --enable-libdav1d --enable-libdavs2 --enable-libdvdread --enable-libdvdnav --disable-libfdk-aac --enable-ffnvcodec --enable-cuda-llvm --enable-frei0r --enable-libgme --enable-libkvazaar --enable-libaribcaption --enable-libass --enable-libbluray --enable-libjxl --enable-libmp3lame --enable-libopus --enable-librist --enable-libssh --enable-libtheora --enable-libvpx --enable-libwebp --enable-libzmq --enable-lv2 --enable-libvpl --enable-openal --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenh264 --enable-libopenjpeg --enable-libopenmpt --enable-librav1e --enable-librubberband --enable-schannel --enable-sdl2 --enable-libsoxr --enable-libsrt --enable-libsvtav1 --enable-libtwolame --enable-libuavs3d --disable-libdrm --enable-vaapi --enable-libvidstab --enable-vulkan --enable-libshaderc --enable-libplacebo --enable-libvvenc --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxvid --enable-libzimg --enable-libzvbi --extra-cflags=-DLIBTWOLAME_STATIC --extra-cxxflags= --extra-libs=-lgomp --extra-ldflags=-pthread --extra-ldexeflags= --cc=x86_64-w64-mingw32-gcc --cxx=x86_64-w64-mingw32-g++ --ar=x86_64-w64-mingw32-gcc-ar --ranlib=x86_64-w64-mingw32-gcc-ranlib --nm=x86_64-w64-mingw32-gcc-nm --extra-version=20240921
libavutil 59. 37.100 / 59. 37.100
libavcodec 61. 17.100 / 61. 17.100
libavformat 61. 6.100 / 61. 6.100
libavdevice 61. 2.101 / 61. 2.101
libavfilter 10. 3.100 / 10. 3.100
libswscale 8. 2.100 / 8. 2.100
libswresample 5. 2.100 / 5. 2.100
libpostproc 58. 2.100 / 58. 2.100
Input #0, flac, from 'C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/Kavinsky - Nightcall.flac':
Metadata:
TITLE : Nightcall
ARTIST : Kavinsky
ALBUM : Nightcall
track : 1
disc : 1
DATE : 2012-10-22
LENGTH : 257000
BPM : 91.1
PUBLISHER : Digital Distribution Serbia
ISRC : FRS710900410
LYRICS : I'm giving you a night call to tell you how I feel
: I want to drive you through the night, down the hills
: I'm gonna tell you something you don't want to hear
: I'm gonna show you where it's dark, but have no fear
:
: There something inside you
: It's hard to explain
: They're talking about you boy
: But you're still the same
:
: There something inside you
: It's hard to explain
: They're talking about you boy
: But you're still the same
:
: I'm giving you a night call to tell you how I feel
: I want to drive you through the night, down the hills
: I'm gonna tell you something you don't want to hear
: I'm gonna show you where it's dark, but have no fear
:
: There something inside you
: It's hard to explain
: They're talking about you boy
: But you're still the same
:
: There something inside you
: It's hard to explain
: They're talking about you boy
: But you're still the same
:
: There something inside you (there's something inside you)
: It's hard to explain (it's hard to explain )
: They're talking about you boy (they're talking about you boy)
: But you're still the same
Duration: 00:04:17.32, start: 0.000000, bitrate: 1015 kb/s
Stream #0:0: Audio: flac, 44100 Hz, stereo, s16
Stream #0:1: Video: mjpeg (Progressive), yuvj444p(pc, bt470bg/unknown/unknown), 800x800 [SAR 300:300 DAR 1:1], 90k tbr, 90k tbn (attached pic)
Metadata:
comment : Cover (front)
Stream mapping:
Stream #0:1 -> #0:0 (copy)
Output #0, image2, to 'C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/cover.jpg':
Metadata:
TITLE : Nightcall
ARTIST : Kavinsky
ALBUM : Nightcall
track : 1
disc : 1
DATE : 2012-10-22
LENGTH : 257000
BPM : 91.1
PUBLISHER : Digital Distribution Serbia
ISRC : FRS710900410
LYRICS : I'm giving you a night call to tell you how I feel
: I want to drive you through the night, down the hills
: I'm gonna tell you something you don't want to hear
: I'm gonna show you where it's dark, but have no fear
:
: There something inside you
: It's hard to explain
: They're talking about you boy
: But you're still the same
:
: There something inside you
: It's hard to explain
: They're talking about you boy
: But you're still the same
:
: I'm giving you a night call to tell you how I feel
: I want to drive you through the night, down the hills
: I'm gonna tell you something you don't want to hear
: I'm gonna show you where it's dark, but have no fear
:
: There something inside you
: It's hard to explain
: They're talking about you boy
: But you're still the same
:
: There something inside you
: It's hard to explain
: They're talking about you boy
: But you're still the same
:
: There something inside you (there's something inside you)
: It's hard to explain (it's hard to explain )
: They're talking about you boy (they're talking about you boy)
: But you're still the same
encoder : Lavf61.6.100
Stream #0:0: Video: mjpeg (Progressive), yuvj444p(pc, bt470bg/unknown/unknown), 800x800 [SAR 300:300 DAR 1:1], q=2-31, 90k tbr, 90k tbn (attached pic)
Metadata:
comment : Cover (front)
Press [q] to stop, [?] for help
[image2 @ 000002195b8ba880] The specified filename 'C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/cover.jpg' does not contain an image sequence pattern or a pattern is invalid.
[image2 @ 000002195b8ba880] Use a pattern such as %03d for an image sequence or use the -update option (with -frames:v 1 if needed) to write a single image.
[out#0/image2 @ 000002195b85e640] video:74KiB audio:0KiB subtitle:0KiB other streams:0KiB global headers:0KiB muxing overhead: unknown
frame= 1 fps=0.0 q=-1.0 Lsize=N/A time=N/A bitrate=N/A speed=N/A
Cover extracted with ffmpeg.
Done.
Extracting metadata...
TITLE=Nightcall
ARTIST=Kavinsky
ALBUM=Nightcall
TRACKNUMBER=1
DISCNUMBER=1
DATE=2012-10-22
LENGTH=257000
BPM=91.1
PUBLISHER=Digital Distribution Serbia
ISRC=FRS710900410
BARCODE=
LYRICS=I'm giving you a night call to tell you how I feel
I want to drive you through the night, down the hills
I'm gonna tell you something you don't want to hear
I'm gonna show you where it's dark, but have no fear

There something inside you
It's hard to explain
They're talking about you boy
But you're still the same

There something inside you
It's hard to explain
They're talking about you boy
But you're still the same

I'm giving you a night call to tell you how I feel
I want to drive you through the night, down the hills
I'm gonna tell you something you don't want to hear
I'm gonna show you where it's dark, but have no fear

There something inside you
It's hard to explain
They're talking about you boy
But you're still the same

There something inside you
It's hard to explain
They're talking about you boy
But you're still the same

There something inside you (there's something inside you)
It's hard to explain (it's hard to explain )
They're talking about you boy (they're talking about you boy)
But you're still the same
{'title': 'Nightcall', 'artist': 'Kavinsky', 'album': 'Nightcall', 'year': '2012-10-22', 'track_no': '1', 'bpm': '91.1', 'lyrics': "I'm giving you a night call to tell you how I feel\r\nI want to drive you through the night, down the hills\r\nI'm gonna tell you something you don't want to hear\r\nI'm gonna show you where it's dark, but have no fear\r\n\r\nThere something inside you\r\nIt's hard to explain\r\nThey're talking about you boy\r\nBut you're still the same\r\n\r\nThere something inside you\r\nIt's hard to explain\r\nThey're talking about you boy\r\nBut you're still the same\r\n\r\nI'm giving you a night call to tell you how I feel\r\nI want to drive you through the night, down the hills\r\nI'm gonna tell you something you don't want to hear\r\nI'm gonna show you where it's dark, but have no fear\r\n\r\nThere something inside you\r\nIt's hard to explain\r\nThey're talking about you boy\r\nBut you're still the same\r\n\r\nThere something inside you\r\nIt's hard to explain\r\nThey're talking about you boy\r\nBut you're still the same\r\n\r\nThere something inside you (there's something inside you)\r\nIt's hard to explain (it's hard to explain )\r\nThey're talking about you boy (they're talking about you boy)\r\nBut you're still the same", 'barcode': '', 'isrc': 'FRS710900410', 'cover': 'C:\Users\emiso\stemgen\output\Kavinsky - Nightcall\cover.jpg'}
Creating tags.json...
Done.
Converting to wav and/or downsampling...

Input File : 'C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/Kavinsky - Nightcall.flac'
Channels : 2
Sample Rate : 44100
Precision : 16-bit
Duration : 00:04:17.32 = 11347812 samples = 19299 CDDA sectors
File Size : 32.7M
Bit Rate : 1.02M
Sample Encoding: 16-bit FLAC
Comments :
TITLE=Nightcall
ARTIST=Kavinsky
ALBUM=Nightcall
TRACKNUMBER=1
DISCNUMBER=1
DATE=2012-10-22
LENGTH=257000
BPM=91.1
PUBLISHER=Digital Distribution Serbia
ISRC=FRS710900410
BARCODE=
LYRICS=I'm giving you a night call to tell you how I feel
I want to drive you through the night, down the hills
I'm gonna tell you something you don't want to hear
I'm gonna show you where it's dark, but have no fear

There something inside you
It's hard to explain
They're talking about you boy
But you're still the same

There something inside you
It's hard to explain
They're talking about you boy
But you're still the same

I'm giving you a night call to tell you how I feel
I want to drive you through the night, down the hills
I'm gonna tell you something you don't want to hear
I'm gonna show you where it's dark, but have no fear

There something inside you
It's hard to explain
They're talking about you boy
But you're still the same

There something inside you
It's hard to explain
They're talking about you boy
But you're still the same

There something inside you (there's something inside you)
It's hard to explain (it's hard to explain )
They're talking about you boy (they're talking about you boy)
But you're still the same

In:100% 00:04:17.32 [00:00:00.00] Out:11.3M [!=====|=====!] Hd:0.0 Clip:0
Done.
Done.
Ready!
Creating a Stem file for Kavinsky - Nightcall...
Splitting stems...
Using 16-bit model...
Selected model is a bag of 1 models. You will see that many progress bars per track.
Separated tracks will be stored in C:\Users\emiso\stemgen\output\Kavinsky - Nightcall\htdemucs
Separating track C:\Users\emiso\stemgen\output\Kavinsky - Nightcall\Kavinsky - Nightcall.flac
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in run_code
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\demucs_main
.py", line 10, in
main()
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\demucs\separate.py", line 173, in main
sources = apply_model(model, wav[None], device=args.device, shifts=args.shifts,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\demucs\apply.py", line 187, in apply_model
sub_model.to(device)
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1174, in to
return self._apply(convert)
^^^^^^^^^^^^^^^^^^^^
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 780, in _apply
module._apply(fn)
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 780, in _apply
module._apply(fn)
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 780, in _apply
module._apply(fn)
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 805, in apply
param_applied = fn(param)
^^^^^^^^^
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1160, in convert
return t.to(
^^^^^
File "C:\Users\emiso\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\cuda_init
.py", line 314, in _lazy_init
torch._C._cuda_init()
RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx
Done.
Creating stem...

[Done 0/6]

converting C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/Kavinsky - Nightcall.wav to alac...
ffmpeg version N-117094-g2bf588f273-20240921 Copyright (c) 2000-2024 the FFmpeg developers
built with gcc 14.2.0 (crosstool-NG 1.26.0.106_ed12fa6)
configuration: --prefix=/ffbuild/prefix --pkg-config-flags=--static --pkg-config=pkg-config --cross-prefix=x86_64-w64-mingw32- --arch=x86_64 --target-os=mingw32 --enable-gpl --enable-version3 --disable-debug --enable-shared --disable-static --disable-w32threads --enable-pthreads --enable-iconv --enable-zlib --enable-libfreetype --enable-libfribidi --enable-gmp --enable-libxml2 --enable-lzma --enable-fontconfig --enable-libharfbuzz --enable-libvorbis --enable-opencl --disable-libpulse --enable-libvmaf --disable-libxcb --disable-xlib --enable-amf --enable-libaom --enable-libaribb24 --enable-avisynth --enable-chromaprint --enable-libdav1d --enable-libdavs2 --enable-libdvdread --enable-libdvdnav --disable-libfdk-aac --enable-ffnvcodec --enable-cuda-llvm --enable-frei0r --enable-libgme --enable-libkvazaar --enable-libaribcaption --enable-libass --enable-libbluray --enable-libjxl --enable-libmp3lame --enable-libopus --enable-librist --enable-libssh --enable-libtheora --enable-libvpx --enable-libwebp --enable-libzmq --enable-lv2 --enable-libvpl --enable-openal --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenh264 --enable-libopenjpeg --enable-libopenmpt --enable-librav1e --enable-librubberband --enable-schannel --enable-sdl2 --enable-libsoxr --enable-libsrt --enable-libsvtav1 --enable-libtwolame --enable-libuavs3d --disable-libdrm --enable-vaapi --enable-libvidstab --enable-vulkan --enable-libshaderc --enable-libplacebo --enable-libvvenc --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxvid --enable-libzimg --enable-libzvbi --extra-cflags=-DLIBTWOLAME_STATIC --extra-cxxflags= --extra-libs=-lgomp --extra-ldflags=-pthread --extra-ldexeflags= --cc=x86_64-w64-mingw32-gcc --cxx=x86_64-w64-mingw32-g++ --ar=x86_64-w64-mingw32-gcc-ar --ranlib=x86_64-w64-mingw32-gcc-ranlib --nm=x86_64-w64-mingw32-gcc-nm --extra-version=20240921
libavutil 59. 37.100 / 59. 37.100
libavcodec 61. 17.100 / 61. 17.100
libavformat 61. 6.100 / 61. 6.100
libavdevice 61. 2.101 / 61. 2.101
libavfilter 10. 3.100 / 10. 3.100
libswscale 8. 2.100 / 8. 2.100
libswresample 5. 2.100 / 5. 2.100
libpostproc 58. 2.100 / 58. 2.100
[aist#0:0/pcm_s16le @ 0000027f90812fc0] Guessed Channel Layout: stereo
Input #0, wav, from 'C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/Kavinsky - Nightcall.wav':
Duration: 00:04:17.32, bitrate: 1411 kb/s
Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, stereo, s16, 1411 kb/s
Stream mapping:
Stream #0:0 -> #0:0 (pcm_s16le (native) -> alac (native))
Press [q] to stop, [?] for help
Output #0, ipod, to 'C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/Kavinsky - Nightcall.m4a':
Metadata:
encoder : Lavf61.6.100
Stream #0:0: Audio: alac (alac / 0x63616C61), 44100 Hz, stereo, s16p, 128 kb/s
Metadata:
encoder : Lavc61.17.100 alac
[out#0/ipod @ 0000027f9085e000] video:0KiB audio:32445KiB subtitle:0KiB other streams:0KiB global headers:0KiB muxing overhead: 0.036847%
size= 32457KiB time=00:04:17.32 bitrate=1033.3kbits/s speed= 414x

[Done 1/6]

converting C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/htdemucs/Kavinsky - Nightcall/drums.wav to alac...
ffmpeg version N-117094-g2bf588f273-20240921 Copyright (c) 2000-2024 the FFmpeg developers
built with gcc 14.2.0 (crosstool-NG 1.26.0.106_ed12fa6)
configuration: --prefix=/ffbuild/prefix --pkg-config-flags=--static --pkg-config=pkg-config --cross-prefix=x86_64-w64-mingw32- --arch=x86_64 --target-os=mingw32 --enable-gpl --enable-version3 --disable-debug --enable-shared --disable-static --disable-w32threads --enable-pthreads --enable-iconv --enable-zlib --enable-libfreetype --enable-libfribidi --enable-gmp --enable-libxml2 --enable-lzma --enable-fontconfig --enable-libharfbuzz --enable-libvorbis --enable-opencl --disable-libpulse --enable-libvmaf --disable-libxcb --disable-xlib --enable-amf --enable-libaom --enable-libaribb24 --enable-avisynth --enable-chromaprint --enable-libdav1d --enable-libdavs2 --enable-libdvdread --enable-libdvdnav --disable-libfdk-aac --enable-ffnvcodec --enable-cuda-llvm --enable-frei0r --enable-libgme --enable-libkvazaar --enable-libaribcaption --enable-libass --enable-libbluray --enable-libjxl --enable-libmp3lame --enable-libopus --enable-librist --enable-libssh --enable-libtheora --enable-libvpx --enable-libwebp --enable-libzmq --enable-lv2 --enable-libvpl --enable-openal --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenh264 --enable-libopenjpeg --enable-libopenmpt --enable-librav1e --enable-librubberband --enable-schannel --enable-sdl2 --enable-libsoxr --enable-libsrt --enable-libsvtav1 --enable-libtwolame --enable-libuavs3d --disable-libdrm --enable-vaapi --enable-libvidstab --enable-vulkan --enable-libshaderc --enable-libplacebo --enable-libvvenc --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxvid --enable-libzimg --enable-libzvbi --extra-cflags=-DLIBTWOLAME_STATIC --extra-cxxflags= --extra-libs=-lgomp --extra-ldflags=-pthread --extra-ldexeflags= --cc=x86_64-w64-mingw32-gcc --cxx=x86_64-w64-mingw32-g++ --ar=x86_64-w64-mingw32-gcc-ar --ranlib=x86_64-w64-mingw32-gcc-ranlib --nm=x86_64-w64-mingw32-gcc-nm --extra-version=20240921
libavutil 59. 37.100 / 59. 37.100
libavcodec 61. 17.100 / 61. 17.100
libavformat 61. 6.100 / 61. 6.100
libavdevice 61. 2.101 / 61. 2.101
libavfilter 10. 3.100 / 10. 3.100
libswscale 8. 2.100 / 8. 2.100
libswresample 5. 2.100 / 5. 2.100
libpostproc 58. 2.100 / 58. 2.100
[in#0 @ 0000021e0fb4dac0] Error opening input: No such file or directory
Error opening input file C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/htdemucs/Kavinsky - Nightcall/drums.wav.
Error opening input files: No such file or directory
Command '['ffmpeg', '-i', 'C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/htdemucs/Kavinsky - Nightcall/drums.wav', '-c:a', 'alac', '-c:v', 'copy', 'C:\Users\emiso\stemgen\output/Kavinsky - Nightcall/htdemucs/Kavinsky - Nightcall/drums.m4a']' returned non-zero exit status 4294967294.
Done.
Cleaning...
Done.
Success! Have fun :)