syncnet_python How to use this repo?

If I am correct, after downloading the models, I have to run

python run_pipeline.py --videofile /path/to/video.mp4 --reference name_of_video --data_dir /path/to/output
python run_syncnet.py --videofile /path/to/video.mp4 --reference name_of_video --data_dir /path/to/output

and the sync-corrected output will be stored in output_dir/pyavi/video.avi

Is this correct?

Oct 06 '20 23:10 dipam7

No, the output is not sync-corrected. It just gives you an offset and active speaker detection labels.

Oct 07 '20 01:10 joonson

How do I use this repo to sync correct my videos?

Oct 07 '20 02:10 dipam7

Also the offsets.txt is not getting generated for me as mentioned in the README. Just 4 pckl files inside output_dir/pywork/reference_name/

Oct 07 '20 16:10 dipam7

what is the --reference name_of_video? I only have a clip of video for sync, I am not sure what to specify for this input.

Jan 21 '21 02:01 houdajun

No, the output is not sync-corrected. It just gives you an offset and active speaker detection labels.

Do we need to sync it manually using the AV offset? How can we do it?

Feb 02 '21 02:02 houdajun