Guidance Needed for Applying This to Another Sign Language
#2
by
gmallen
- opened
Hello, thank you for sharing your work!
Could you please explain how we could adapt or reproduce this approach for another sign language?
Are there specific steps or resources we should follow?
Hi!
We have almost finished the project. What is still missing is the fine-tuning with the video data, we prepared.
We have a GitHub here with more details. There is also some info on how to prepare the video data for the training here.
Did you check that one already?
We run the tweaked whisper model published here for a simple inference and it worked at that time.
We would be happy if you would like to use the approach.