i was wondering in what way Ircams Rave compares with Flucomas Machine learning tools? GitHub - acids-ircam/RAVE: Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
Are there clear similarities or differences and is there an intersection to them at all?
Not being an expert on Machine Learning and AI, it’s not entirely obvious to me how these compare.
If anyone has an idea or experience be curious to hear!
They are quite different in aims and in scope. RAVE is working on audio material directly. Other threads here talk about it because it is fun FluCoMa ML is simpler, and more geared at symbolic data. An example is controller assignment. Other examples are pattern finding in descriptor spaces. Rebecca Fiebrink was telling us that she saw people joining the 2 concepts successfully: her wekinator to control RAVE-made models.
I recommend playing with both RAVE and the FluCoMa entry level tutorials. They are many ways one could think of plugging them together…
ok i see, thank you @tremblap, will surely try it out!