[Sw-l] GPT for Deaf and Dancing?

[John Carlson]

David and the SW-List,

I had a thought that just like OpenAI's whisper turns audio (possibly in
video)  into textual words, one could take a video of someone using sign
language, and convert that into text.

Once you have the text, then can be fed into something like sgpt (Shell-GPT)

https://www.youtube.com/watch?v=agHO8xpCI0w
https://github.com/TheR1D/shell_gpt

to get a response.

Then one would take the response and convert the response back into sign
language (video).

So I need a video sign language to text converter and a text to sign
language converter (video).   Are they available?

Ultimately, for the deafblind, I want to convert video or text into robotic
control.

I can also see that we could take video and produce DanceWriting, and then
take DanceWriting and convert it to video or robotics.

What do you think?

This is the clearest I've thought on this for a while.  I'm guessing you
guys are on top of this already.  It's time for me to do some googling!

Thanks,

John
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/sw-l/attachments/20230709/d4bc7574/attachment.htm>