sevagh / demucs.cpp

C++17 port of Demucs v3 (hybrid) and v4 (hybrid transformer) models with ggml and Eigen3

Try some of the best drums and bass stem separation available today: https://pro.freemusicdemixer.com/

Demucs in your pocket! Download the Android app today:

demucs.cpp's Issues

Question about GPU

How difficult is it to build this using cuBLAS? I'm looking into creating a native project around demucs but need GPU acceleration. Python is way too bloated for my liking.

CMakeLists.txt demucs.cpp.test target - missing dependency gtest

demucs.cpp.test depends on googletest, which is not vendord or in the README.md.
I can't build that target on macOS. Maybe if I install via homebrew, although I think it might be better to include it as a submodule?

unknown target CPI 'apple-m1'

I am getting this build error since updating to the recent commits:

error: unknown target CPU 'apple-m1'
note: valid target CPU values are: nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, knl, knm, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, x86-64, x86-64-v2, x86-64-v3, x86-64-v4

demucs_mt.cpp.main hard wired for 4-source

The multithreaded cli seems to be hard wired for 4-source models as you can see in this for loop:

demucs.cpp/cli-apps/threaded_inference.hpp

Line 141 in 6f0eba0

for (int t = 0; t < 4; ++t)

Amount of time to demux an audio file

Hi, do you know roughly how long it takes for you to demux an audio file? I've tried with a clip that's 1m30s long, and it took 10m43, so x7 times as long. Is this expected, or have I done something silly?

$ cat /proc/cpuinfo | grep "model name" | head -n1
model name : Intel(R) Core(TM) i3-6100 CPU @ 3.70GHz

(used the 4 sources model).

Thanks!

Feature request - optional logging

Making this a separate issue, although it could be combined with #5.

As demucs.cpp processes the various stages of the algorithm you print the current operation to the std::out which is perhaps undesirable in a library. Could this logging could be made optional or via a callback?

Feature request - better progress reporting and logging

Firstly thanks for this fantastic project and contribution to the world of open source stem separation. I may make a few more PRs to make it build well on macOS and windows, and e.g. add performance measurements with BLAS from Apple's Accelerate.

I would like to suggest an improvement. It's great to have the progress callback, but each pass of the demucs processing is so resource intensive that it can be a while before you get any feedback. In the case where you want to run this on a background thread it would be good to have a more granular progress callback - so that you can check if the user cancelled the processing, which can take a very long time.

Support Demucs v3 (hdemucs_mmi)

Architecture is not too far from v4, except this codebase is missing an LSTM (which I have in umx.cpp: https://github.com/sevagh/umx.cpp/blob/main/src/lstm.cpp)

Still, it will take some effort to trace through every step of v3 inference and implement it all correctly.