audiocraft
audiocraft copied to clipboard
facebookresearch
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 mu...
This commit: https://github.com/pytorch/pytorch/commit/a8329676273ac12f1fadfbcdd19c500d84998345 Released in torch 2.1.0 breaks this https://github.com/facebookresearch/audiocraft/blob/main/audiocraft/optim/fsdp.py#L126 This ticket (https://github.com/facebookresearch/audiocraft/issues/358) has an implementation that works on torch 2.1.0 - but there should probably be some backward compatibility...
There seems to be a mistake in the docstring of `audiocraft.models.lm.LMModel.forward()`. At [https://github.com/facebookresearch/audiocraft/blob/87af0bfddd489c5f22d2ea6743fb4afbe092539e/audiocraft/models/lm.py#L226](https://github.com/facebookresearch/audiocraft/blob/87af0bfddd489c5f22d2ea6743fb4afbe092539e/audiocraft/models/lm.py#L226): ````python def forward(self, sequence: torch.Tensor, conditions: tp.List[ConditioningAttributes], condition_tensors: tp.Optional[ConditionTensors] = None, stage: int = -1) -> torch.Tensor:...
I am currently exploring the musicgen model and have some questions regarding the application of audio prompts within the model's architecture, particularly in relation to the cross_attention layers: 1. **Role...
Hello, We're trying to run musicgen training/fine-tuning from the audiocraft repo using dora. We've been able to run single-node training with `dora run -d solver`, When running the above using...
Hello, I have been on the full installation of musicgen(audiocraft) on google colabs for more than 20 hours and there are conflicts with torch, torchaudio...... and so on...... Do you...
I would like to perform finetuning on a small musicgen model. I have a dataset consisting of different short sounds. Actually, it's not big. But I successfully trained on the...
When I train musicgen model using a small training set, the training process can proceed normally. However, when I switch to a larger training set, which includes about 20000 samples,...
I trained a 16khz 4-band diffusion model on the whole AudioSet, but the model can not generate correct audio during the inference stage. It can only generate white noise audio....
There seems to be an error in loading the model when trying to run the codes on Google Colab whereby it gives the following error as attached. 
Please update the license for AudioCraft projects, so that like LLama by Meta, they have commercial license. Thanks for your consideration.
Metadata
Owner
Metadata
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 mu...