facebookresearch/AudioMAE

Issues

• converting the resulting fbank back to .wav?

  #28 opened 3 months ago by Desync-o-tron
  0

• Issues with loading model weights to reproduce the demo notebook

  #12 opened 2 years ago by bpiyush
  2

• kaldi fbank

  #25 opened 10 months ago by lix4
  1

• VIT-L checkpoint and reproducing the visualization results

  #20 opened a year ago by i-need-sleep
  3

• Question Regarding _roll_mag_aug Function Implementation in AudioMAE

  #26 opened 8 months ago by unoct
  0

• where is 2M audioset data and pretrain_audioset2M.sh?

  #21 opened a year ago by JHjang223
  2

• Unable to utilize main_pretrain.py for speechcommands dataset training

  #16 opened 8 months ago by unoct
  1

• Cannot reproduce finetuning result on Audioset-20k

  #23 opened a year ago by kxgong
  0

• RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.

  #24 opened a year ago by wuhongsheng
  1

• Submitted job triggered an exception

  #22 opened a year ago by wuhongsheng
  0

• When will you release the code?

  #6 opened a year ago by jinx2018
  0

• When will you release the code?

  #4 opened a year ago by linmou
  0

• reproduce inference results

  #19 opened a year ago by hanlin-lu
  0

• Can't find train_all_video.json for main_pretrain.py

  #18 opened a year ago by joo-young-lee
  0

• Can't download any ckpt files in github

  #17 opened a year ago by joo-young-lee
  1

• Could u release the finetuned checkpoint of dataset 'AudioSet20K' ?

  #15 opened a year ago by yanjies
  0

• May I ask how to visualize the data in esc50

  #14 opened a year ago by yangyangshuyang
  0

• Reproducing the downstream task performance

  #8 opened 2 years ago by Sara-Ahmed
  1

• Vit-S pretraining checkpoint

  #13 opened 2 years ago by G-JWLee
  0

• Could u release self-supervised weights without fine-tuning?

  #11 opened 2 years ago by haidog-yaqub
  1

• where is the weight_train.csv?

  #9 opened 2 years ago by LinB203
  1

• Where is the mae_env.yml ?

  #10 opened 2 years ago by unoct
  1

• Evaluation on ASR

  #7 opened 2 years ago by LeyuanQu
  0

• Open Sourcing through Hugging Face

  #5 opened 2 years ago by osanseviero
  0

• When will you release the code?

  #2 opened 2 years ago by hou821
  2

• Do you think this work will apply to music super resolution task

  #3 opened 2 years ago by mengdexing
  1

• goodwork

  #1 opened 2 years ago by qixing-ai
  1