AMAAI-Lab/mustango

Issues

• this is no 'pytorch_model_main.bin' in mustango 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"))

  #13 opened 9 months ago by bocaidoufuyushiren
  1

• Music generation time

  #10 opened 8 months ago by TLNTrung
  1

• [Error] ImportError: cannot import name 'UNet2DConditionModelMusic' from 'diffusers'

  #2 opened 8 months ago by syddharth
  3

• Music duration

  #11 opened 8 months ago by qiao131
  1

• How to install mustango?

  #3 opened a year ago by tin2tin
  6

• Line 606, file train.py "need to pass the audio here instead of 'text' "

  #12 opened a year ago by nikifori
  0

• Possible pipeline

  #9 opened a year ago by TLNTrung
  4

• Training device and time

  #7 opened a year ago by fundwotsai2001
  2

• when and how should i download the audioldm/audioldm-s-full.ckpt

  #6 opened a year ago by fundwotsai2001
  1

• Can't run after finish installation in Google Colab

  #8 opened a year ago by TLNTrung
  1

• FMACaps

  #5 opened a year ago by wwfcnu
  1