Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
MIT License
20.18k
stars
2.01k
forks
source link
SUGGESTION: add support for "clean" sample endings #365
Consider adding support (parameters, functions, etc.) to create tonally "clean" endings to samples. Currently, samples are truncated by time. Would be cool if the model allowed a user to specify an ending type, e.g., Reverse Reverb Tail, Resolving Melodic Line, Filter Sweep, Loop and Fade, Closing Note. Or create a function that's, effectively, continuation in reverse; accepts an input sample and a duration but works toward ending the track in the time specified by duration rather than extending it.
Consider adding support (parameters, functions, etc.) to create tonally "clean" endings to samples. Currently, samples are truncated by time. Would be cool if the model allowed a user to specify an ending type, e.g., Reverse Reverb Tail, Resolving Melodic Line, Filter Sweep, Loop and Fade, Closing Note. Or create a function that's, effectively, continuation in reverse; accepts an input sample and a duration but works toward ending the track in the time specified by duration rather than extending it.