Issues

• Model download using git LFS fails

  dmlguq456/SepReformer#31 · Filter by author samtiz opened on Jun 30, 2025
  1

• valid_loss_best is re-initialized every epoch

  dmlguq456/SepReformer#28 · Filter by author Nitsu22 opened on May 18, 2025

• Pretrained weights for SepReformer Large_DM_WHAMR model

  dmlguq456/SepReformer#27 · Filter by author ZhenziWeng opened on May 15, 2025
  2

• Local Path in Training

  dmlguq456/SepReformer#26 · Filter by author sean-mccrthy opened on Apr 24, 2025

• Could you please clarify

  dmlguq456/SepReformer#25 · Filter by author xlzhou01 opened on Mar 5, 2025

• for inference

  dmlguq456/SepReformer#24 · Filter by author johney0301 opened on Feb 6, 2025
  1

• Inference problem

  dmlguq456/SepReformer#23 · Filter by author Youssef-Barakat opened on Dec 29, 2024

• How can one separate two speakers who speak simultaneously?

  dmlguq456/SepReformer#22 · Filter by author MonolithFoundation opened on Dec 13, 2024

• RuntimeError: Could not infer dtype of numpy.float32

  dmlguq456/SepReformer#21 · Filter by author Youjin1985 opened on Dec 11, 2024

• AttributeError: 'MyDataset' object has no attribute 'speed_aug'

  dmlguq456/SepReformer#18 · Filter by author taqta opened on Nov 21, 2024

• Timestamps?

  dmlguq456/SepReformer#17 · Filter by author LostnD opened on Nov 11, 2024

• How do I run this model in python code?

  dmlguq456/SepReformer#16 · Filter by author PhilipAmadasun opened on Oct 30, 2024

• Pretrained model performs poorly on my audio, not sure why

  dmlguq456/SepReformer#15 · Filter by author PhilipAmadasun opened on Oct 30, 2024

• The model can run in real-time? Or does it have the potential to be modified into a real-time model?

  dmlguq456/SepReformer#14 · Filter by author haha010508 opened on Oct 25, 2024

• _pickle.UnpicklingError: invalid load key, 'v'.

  dmlguq456/SepReformer#12 · Filter by author simplcup opened on Oct 21, 2024
  6

• Can this audio encoder handle 3 to 4 minutes of audio?thank you

  dmlguq456/SepReformer#8 · Filter by author speech26ai opened on Oct 15, 2024
  1

• Seperation on more than 2 person audio

  dmlguq456/SepReformer#7 · Filter by author MonolithFoundation opened on Oct 12, 2024
  3

• Thanks for your excellent work.How can I directly inference a single audio?

  dmlguq456/SepReformer#6 · Filter by author seetimee opened on Oct 12, 2024
  1

• How can i train a model with a Libri2Mix Dataset?

  dmlguq456/SepReformer#5 · Filter by author IXackerr opened on Jul 12, 2024
  1

• Models

  dmlguq456/SepReformer#3 · Filter by author rnehrboss opened on Jul 8, 2024
  6

• Nan in loss function

  dmlguq456/SepReformer#2 · Filter by author hieugiaosu opened on Jul 7, 2024

• WJS- Dataset

  dmlguq456/SepReformer#1 · Filter by author arrrrr3186 opened on Jul 1, 2024
  1