Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / facebookresearch/AudioMAE issues and pull requests

#30 - ESC-50/Speechcommands recipe/documentation

Issue - State: open - Opened by IvanBirkmaier about 2 months ago

#29 - Linear probing recipe missing

Issue - State: open - Opened by Peipi98 3 months ago

#28 - converting the resulting fbank back to .wav?

Issue - State: open - Opened by Desync-o-tron 5 months ago

#27 - [BUG] No module named 'torch._six'

Pull Request - State: open - Opened by ps4vs 8 months ago - 2 comments
Labels: CLA Signed

#27 - [BUG] No module named 'torch._six'

Pull Request - State: open - Opened by ps4vs 8 months ago - 2 comments
Labels: CLA Signed

#25 - kaldi fbank

Issue - State: open - Opened by lix4 about 1 year ago - 1 comment

#23 - Cannot reproduce finetuning result on Audioset-20k

Issue - State: open - Opened by kxgong about 1 year ago

#22 - Submitted job triggered an exception

Issue - State: closed - Opened by wuhongsheng over 1 year ago

#21 - where is 2M audioset data and pretrain_audioset2M.sh?

Issue - State: open - Opened by JHjang223 over 1 year ago - 3 comments

#20 - VIT-L checkpoint and reproducing the visualization results

Issue - State: open - Opened by i-need-sleep over 1 year ago - 3 comments

#19 - reproduce inference results

Issue - State: open - Opened by hllmathcs over 1 year ago

#18 - Can't find train_all_video.json for main_pretrain.py

Issue - State: open - Opened by joo-young-lee over 1 year ago

#17 - Can't download any ckpt files in github

Issue - State: closed - Opened by joo-young-lee over 1 year ago - 1 comment

#16 - Unable to utilize main_pretrain.py for speechcommands dataset training

Issue - State: closed - Opened by unoct over 1 year ago - 1 comment

#14 - May I ask how to visualize the data in esc50

Issue - State: open - Opened by yangyangshuyang over 1 year ago

#13 - Vit-S pretraining checkpoint

Issue - State: open - Opened by G-JWLee over 1 year ago

#12 - Issues with loading model weights to reproduce the demo notebook

Issue - State: open - Opened by bpiyush almost 2 years ago - 2 comments

#11 - Could u release self-supervised weights without fine-tuning?

Issue - State: closed - Opened by haidog-yaqub almost 2 years ago - 1 comment

#10 - Where is the mae_env.yml ?

Issue - State: closed - Opened by unoct almost 2 years ago - 1 comment

#9 - where is the weight_train.csv?

Issue - State: closed - Opened by LinB203 almost 2 years ago - 1 comment

#8 - Reproducing the downstream task performance

Issue - State: open - Opened by Sara-Ahmed almost 2 years ago - 1 comment

#7 - Evaluation on ASR

Issue - State: open - Opened by LeyuanQu almost 2 years ago

#6 - When will you release the code?

Issue - State: closed - Opened by jinx2018 about 2 years ago

#5 - Open Sourcing through Hugging Face

Issue - State: open - Opened by osanseviero about 2 years ago

#4 - When will you release the code?

Issue - State: closed - Opened by linmou over 2 years ago

#3 - Do you think this work will apply to music super resolution task

Issue - State: closed - Opened by mengdexing over 2 years ago - 1 comment

#2 - When will you release the code?

Issue - State: closed - Opened by hou821 over 2 years ago - 2 comments

#1 - goodwork

Issue - State: closed - Opened by qixing-ai over 2 years ago - 1 comment