umx.cpp
free-music-demixer
| umx.cpp | free-music-demixer | |
|---|---|---|
| 1 | 7 | |
| 28 | 323 | |
| - | - | |
| 5.8 | 8.0 | |
| 4 months ago | about 1 month ago | |
| C++ | Python | |
| MIT License | MIT License |
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.
umx.cpp
-
Show HN: Free AI-based music demixing in the browser
Good question! So, I wasn't even thinking about WASM to begin with. When I saw llama.cpp and whisper.cpp on the front page of HN, I found the idea exciting - instead of neural networks being magic, I wanted to copy the ggml idea of parsing the PyTorch weights file myself and rewriting the inference code in a lower-level language than Python (or, it's even more accurate to say PyTorch, since there is so much matrix heavy lifting e.g. broadcasting or reshaping that is done for you automatically).
That's when I wrote umx.cpp [1] (which is what this site is based on).
On an unrelated project, a friend of mine mentioned WASM, and as I looked into it a bit more I thought trying to compile umx.cpp to WASM would be a great idea, since I only use Eigen (which is a header-only library that only depends on std).
1: https://github.com/sevagh/umx.cpp
free-music-demixer
- Ask HN: What are some of the best user experiences with AI?
-
Free-music-demixer adds multi-threading to run Demucs faster in the browser
Hi HN,
Over the Christmas break I added multi-threading to the WASM Demucs module in freemusicdemixer
Demucs (v4 hybrid transformer) is a much higher quality model than the previous default, but it ran very slowly when limited to one worker: ~17 minutes for an average 4-minute song
I have since implemented multi-threading with WebWorkers.
If you raise the "MAX MEMORY" setting to 16 GB or 32 GB, your track will demix within 7-5 minutes, producing state-of-the-art results.
There is also support for the Demucs 6-source model which adds piano and guitar stems.
Please reach out and be loud about any bugs or UX issues you encounter!: https://github.com/sevagh/free-music-demixer/issues
- Show HN: Improved freemusicdemixer – AI music demixing in the browser
- Show HN: Improved freemusicdemixer (AI music demixing in the browser)
- FLaNK Stack Weekly for 17 July 2023
-
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...
What are some alternatives?
1000sharks.xyz - AI "metal artist" with SampleRNN (mirror from GitLab)
danswer - Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.
EfficientAT - This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.
open-unmix-pytorch - Open-Unmix - Music Source Separation for PyTorch
heimdall - Dashboard for operating Flink jobs and deployments.
dt - dt - duct tape for your unix pipes
video2dataset - Easily create large video dataset from video urls
khoj - Your AI second brain. A copilot to get answers to your questions, whether they be from your own notes or from the internet. Use powerful, online (e.g gpt4) or private, local (e.g mistral) LLMs. Self-host locally or use our web app. Access from Obsidian, Emacs, Desktop app, Web or Whatsapp.
plate - The rich-text editor for React.
lima - Linux virtual machines, with a focus on running containers