MNeMoNiCuZ/AThousandWords: A captioning suite that combines many different captioning models in one place, with a GUI, CLI and input args.

https://github.com/MNeMoNiCuZ/AThousandWords

7 points · 3 comments · view on lemmy.world

3 Comments

Peekashoe@lemmy.wtf · 1 pts · 184d
[ removed ]
Peekashoe@lemmy.wtf · 1 pts · 184d (2 replies)

I can't quite tell from the page but I am assuming this aids in pre-training captioning, not in providing captions (subtitles) to e.g. video content?

Even_Adder@lemmy.dbzer0.com · 2 pts · 184d (1 reply)

Correct.

Peekashoe@lemmy.wtf · 1 pts · 184d

Thank you.

And wow, all of those error-failed comments actually posted. Sorry, I'll try to delete them. The instance has been slow.

Peekashoe@lemmy.wtf · 1 pts · 184d
[ removed ]
Peekashoe@lemmy.wtf · 1 pts · 184d
[ removed ]
Peekashoe@lemmy.wtf · 1 pts · 184d
[ removed ]
Peekashoe@lemmy.wtf · 1 pts · 184d
[ removed ]