Replies: 1 comment
-
|
Done, found out i just need to make it dont bind it together |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
So, i managed to connect BallonsTranslator with local LLM AI, but the issue is from this point.
when it translated from the scanned text, they indeed correct most of the time, but the issue was they seems merging the text
example from the apps was
<|1|> first sentence
<|2|> second
<|3|> third
but instead had output like
<|1|> translated first sentence
<|2|> translated second
<|3|> translated third
they give me
"this long translated sentence"
so the BallonsTranslator seems not recognize the result and mark as invalid, when on panel which only had 1 text, they translated it with no problem
so question here.... how can i make the translated result was as same as the input
like... 3 line of text
translated as 3 line of text too instead merging or more than that
already said keep the format, or dont merge the result, they keep happening lol
Beta Was this translation helpful? Give feedback.
All reactions