HP: https://github.com/deezer/spleeter
Lizenz: MIT
Beschreibung:
Mit Spleeter kann man einzelne Instrumentenspuren wie Bass, Schlagzeug, Vocals aus Songs extrahieren. Wer lieber statt mit performanter CLI per GUI arbeitet, wird mit spleeter for max glücklicher: https://github.com/diracdeltas/spleeter ... er-for-maxSpleeter is Deezer source separation library with pretrained models written in Python and uses Tensorflow. It makes it easy to train source separation model (assuming you have a dataset of isolated sources), and provides already trained state of the art model for performing various flavour of separation :
Vocals (singing voice) / accompaniment separation (2 stems)
Vocals / drums / bass / other separation (4 stems)
Vocals / drums / bass / piano / other separation (5 stems)
2 stems and 4 stems models have high performances on the musdb dataset. Spleeter is also very fast as it can perform separation of audio files to 4 stems 100x faster than real-time when run on a GPU.
Ich habe es nicht getestet, aber es klingt doch ziemlich interessant und mit Deezer ist ja auch jemand mit Sachverstand dabei.