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.
Using MusicGen, the sound is playing at the wrong "speed". The synthesis sounds like a fast granular synthesis played at a fast speed.
— I tried to change the sampling rate of the input audiofile to 32kHz etc.
— I also have the problem with the "assets" demo soundfiles.
— Default or Multiband Diffusion does not change.
— I have the following warning; even if I doubt it is the problem:
warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
— I am running it on CPU on Apple Silicon...
— I bypassed everything about "xformers" in transformer.py. "xformers" does not work on Apple Silicon.
Hello!
Using MusicGen, the sound is playing at the wrong "speed". The synthesis sounds like a fast granular synthesis played at a fast speed.
— I tried to change the sampling rate of the input audiofile to 32kHz etc. — I also have the problem with the "assets" demo soundfiles. — Default or Multiband Diffusion does not change. — I have the following warning; even if I doubt it is the problem: warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") — I am running it on CPU on Apple Silicon... — I bypassed everything about "xformers" in transformer.py. "xformers" does not work on Apple Silicon.