Polymath is a open-source tool that converts any music-library into a sample-library with machine learning. It separates songs into stems, quantizes to same BPM, detects key and much more. A game-changing workflow for music producers & DJ
Other cool #aiart things:<p>- "MusicLM: Generating music from text" <a href="https://news.ycombinator.com/item?id=34543748" rel="nofollow">https://news.ycombinator.com/item?id=34543748</a><p>- /? awesome Generative AI site:GitHub.com
<a href="https://www.google.com/search?q=awesome+generative+ai+site%3Agithub.com" rel="nofollow">https://www.google.com/search?q=awesome+generative+ai+site%3...</a><p>- #GenerativeArt #GenerativeMusic<p>- BespokeSynth DAW: <a href="https://github.com/BespokeSynth/BespokeSynth">https://github.com/BespokeSynth/BespokeSynth</a> :<p>> [...] <i>live-patchable environment, so you can build while the music is playing; VST, VST3, LV2 hosting;
Python livecoding; </i> MIDI, [...]
> <i>Using Polymath's search capability to discover related tracks, it is a breeze to create a polished, hour-long mash-up DJ set</i><p><a href="https://github.com/samim23/polymath#how-does-it-work">https://github.com/samim23/polymath#how-does-it-work</a> :<p>> <i>How does it work?</i><p>> <i>- Music Source Separation is performed with the [facebook/demucs] neural network</i><p>> <i>- Music Structure Segmentation/Labeling is performed with the [wayne391/sf_segmenter] neural network</i><p>> <i>- Music Pitch Tracking and Key Detection are performed with [marl/Crepe] neural network</i><p>> <i>- Music Quantization and Alignment are performed with [bmcfee/pyrubberband]</i><p>> <i>- Music Info retrieval and processing is performed with [librosa/librosa]</i>
Bloody hell...seriously...the rate at which stuff comes out is just baffling.
samim - do you have examples of this in use? I've kinda dreamed of something like this for some time!