Stars
Deezer source separation library including pretrained models.
zero-shot voice conversion & singing voice conversion, with real-time support
WavJourney: Compositional Audio Creation with LLMs
GUI for a Vocal Remover that uses Deep Neural Networks.
Easily train a good VC model with voice data <= 10 mins!
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)