mustango
mustango copied to clipboard
Mustango: Toward Controllable Text-to-Music Generation
Pip doesn't work, nor does git cloning? Running the QuickGuide example, mustango needs to be installed as python module?
this is no 'pytorch_model_main.bin' in mstango of huggingface.but in code train.py row395 : model.load_state_dict(torch.load("{}/pytorch_model_main.bin".format(hf_model_path), map_location="cpu")) how can I finetune this model?
What do you mean by saying "need to pass the audio here instead of 'text' " in line 606 of file train.py?
There is a question about the time to generate music, can only generate 10s at most?
In line 10 of the Quickstart Guide: `sf.write(f"{prompt}.wav", audio, samplerate=16000)` The variable `audio` is used but never declared or defined. To fix this, it should be replaced with the variable...
Dear MusicTango Team, I hope you're doing well. I’ve been exploring the Audioldm_eval tool from your GitHub (https://github.com/haoheliu/audioldm_eval) and truly appreciate the work. While reviewing the paper and code, I...