open-unmix-pytorch
stemroller
Our great sponsors
open-unmix-pytorch | stemroller | |
---|---|---|
11 | 37 | |
1,157 | 2,399 | |
2.3% | 3.6% | |
0.0 | 3.1 | |
11 days ago | 7 days ago | |
Python | Svelte | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
open-unmix-pytorch
-
Show HN: Improved freemusicdemixer (AI music demixing in the browser)
In my first post, quite a lot of alternatives were discussed: https://news.ycombinator.com/item?id=36707877
The model I'm using is called Open-Unmix (https://github.com/sigsep/open-unmix-pytorch). In 2021, there was an update to Open-Unmix to include new weights, UMX-L, which made it perform better than it used to on the older weights (UMXHQ).
In the grand landscape of music demixing, I don't think UMX-L is near the top anymore.
_However_, the demixing performance of freemusicdemixer.com is very close to the full PyTorch performance of Open-Unmix UMX-L, despite the tricks I needed to get it working in the browser, such as splitting up the inference to operate on segments of the song, or making the LSTM operate on streaming segments rather than holding the entire track in the LSTM memory.
In my first release, I loaded and did inference on the entire track at once (like the PyTorch model), which frequently crashed or exceeded the 4GB WASM memory for medium or large-size tracks.
-
Show HN: Free AI-based music demixing in the browser
* Post-processing step (bigger impact)
I tried to tackle the post-processing step in my C++ code (which would win ~1 dB in quality across all targets) but it's too tricky for now [2]. Maybe some other day.
1: https://github.com/sevagh/free-music-demixer/blob/main/examp...
2: https://github.com/sigsep/open-unmix-pytorch/blob/master/ope...
-
Splitter.fm: Listen to the individual instrument/vocal tracks (known as "stems") for over 700 songs uploaded by 150+ artists
Or open-unmix. I've found it performs better than spleeter in some of my tests.
- I've created a website that extracts audio stems from songs using Spleeter, Demucs3, and Open Unmix for free.
-
Cassiopeia: New Audio Splitter Superior to Spleeter and UMX
There's maybe something useful for you here?
https://github.com/facebookresearch/demucs
https://github.com/sigsep/open-unmix-pytorch
https://github.com/bytedance/music_source_separation
https://github.com/deezer/spleeter
- [N] Music Demixing (Audio Source Separation) Competition by Sony | ISMIR 2021
- [N Music Demixing (Audio Source Separation) Competition by Sony | ISMIR 2021
-
[Research] Music Source Separation with AI networks: Comparison Tests incl. Spleeter, Lalal.ai, OpenUnmix and Extended Unmix
OpenUnmix ( is a neural network solution from Yuki Mitsufuji and Stefan Uhlich, music industry luminaries that work in Sony's core divisions.
stemroller
-
Instrument Isolate for foobar2000
Would be possible to make this into a foobar2000 component https://github.com/stemrollerapp/stemroller
-
Show HN: Improved freemusicdemixer (AI music demixing in the browser)
For those interested, Facebook's Demucs page (https://github.com/facebookresearch/demucs) gives performance comparison for several models including open-unmix.
See also: https://www.stemroller.com This runs as a local app on Windows and Mac.
-
How can I find instrumentals of rap songs?
This is a pay as you go service that works pretty well. This one is free and works slightly less better (IMO) than the first. Website makes it sound like you have to use their search function but you can just drag and drop audio files in.
- Drum tracks
- Ich finde Gesang in Musik mehrheitlich störend.
-
[QUESTION] Do you guys have any specific websites with drum tracks for songs or do i just hope the song im after is on youtube?
Try Stemroller (https://github.com/stemrollerapp/stemroller). It can break an mp3 down into individual stems. Very CPU intensive though.
-
Separate soundtrack from voices
I usually try a few options to test for the best results, including Vocalremover and Spleeter, but also https://www.stemroller.com/
-
RTJ acapellas
Stem Roller
-
Why won't Ubisoft isolate the stems so we can only hear our guitar on rocksmith+?
I wonder why ubisoft hasn't used ai to split the tracks in rocksmith. There are tools like https://github.com/stemrollerapp/stemroller that can do it easily. DJs are doing this live with audio they are mixing. It would make the game more fun and realistic. I don't like hearing the original guitar over mine. I wish I could mute it and play solo.
- are Acapellas hard to find?
What are some alternatives?
spleeter - Deezer source separation library including pretrained models.
demucs - Code for the paper Hybrid Spectrogram and Waveform Source Separation, but the goddamm motherfucker doesn't work.
music_source_separation
ultimatevocalremovergui - GUI for a Vocal Remover that uses Deep Neural Networks.
free-music-demixer - free website for client-side music demixing with Demucs + WebAssembly
demucs-cxfreeze
ai-research-code
tortoise-tts-fast - Fast TorToiSe inference (5x or your money back!)
demucs4max - Demucs as a max4live device