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.
This is probably an issue with the config file for the diffusion model. The generation sample rate should be added to the generate and not in dataset.generate
This generate.audio params are passed to audio_write functions save audio using ffmpeg in the following line
What?
This is probably an issue with the config file for the diffusion model. The generation sample rate should be added to the
generateand not indataset.generateThis
generate.audioparams are passed toaudio_writefunctions save audio using ffmpeg in the following linehttps://github.com/facebookresearch/audiocraft/blob/69fea8b290ad1b4b40d28f92d1dfc0ab01dbab85/audiocraft/utils/samples/manager.py#L193
Test