James Fung

Hello Paul, It depends on which Raspberry Pi you own, spoiler alert, you need a little stronger CPU to run SpleeterRT. Last time I check, Raspberry Pi 4 are capable...

5stems model is not open source and probably will never be, sorry about that.

Hello, It doesn't matter much for using different window function to operate, empirically, CNN look for patterns not much on actual value, so that no observable real-world accuracy reduced. Neither...

Since Spleeter U-Net is so simple, I do a full rewritten version in C for real-time(Continuous STFT buffered) lag-less(no frame drop for modern CPU) VST inference. The initialization function allow...

@aidv is right. SpleeterRT is continuous STFT buffered, lag-less(no frame drop for modern CPU). But not real-time algorithmically. @Scylla2020 I'll tell you what, true real-time is not possible without tricks,...

@Scylla2020 Avoid using Python is totally the point, beside Python, SpleeterRT offer flexible intrinsic latency adjustment(How many time frame for the neural network to inference). And well parallelized 4 stems...

@Scylla2020 In short yes. SpleeterRT offer background processing, corresponding to Spleeter4Stems.c. If you use spleeter.c directly for offline inference, you may see sightly faster inference compared to tensorflow-cpu.

@aidv @Scylla2020 DJ software marketing "real time" is not good, but not wrong in definition, "real time" definition first appear in computer as a measures of reaching deadline, however, the...

@junh1024 The site you provided sound like HPSS algorithm, which is almost real time in algorithmic sense. For real time-ness: I guess you understand "Processing time" and "Algorithmic latency". Assume...

Dear contributor @blackball , Simply using MKL routine if MKL were detected in the compiler enviroment, that matrix multiplication performance is beast and basically overhead-free. Well, beside Intel MKL doens't...