>>109003199
Finally

File: Screenshot From 2026-06-07 16-46-00.png (149.2 KB)

it's extremely prone to hallucinations

>>109003199
Don't they have a "cross-attention" architecture specifically for translating? Just make that better instead of prompting gemini flash

Same with search. I often search for song lyrics, and unless I'm very clear in the request that these are lyrics, it gives me advice instead of information about the song.

It's fascinating to see trillion dollar companies fumbling so much. On the one hand it's magical that this is even possible, on the other, it's clear that they're all scrambling. Both genius and amateur hour.

>>109003310
yandex is now better with song lyrics. i can even search the exact title of a youtube video and it will show me "related" or "recommended" videos first

>>109003199
Always was. You are obviously young. You used to be able to make it say creepy phrases by feeding it gibberish.
The transformer architecture was invented by Google for Google Translate.

>>109003332
the underlying architecture has changed. i've been feeding everything from valid sentences, to slang, to utter bullshit and mojibake into translate for years. something has changed about the way it hallucinates. it's much less literal. it clearly engages in chatbot behaviors, such as em-dashes, or even talking about the text in some rare cases instead of attempting to translate it.

Are LLM translations actually good now?
Can you take foreign subtitles and translate them to english and actually get a good result?

>>109003199
It's been for a while. I knew it was for sure when translations stopped being too literal, it's a subtle shift.

File: spongebob_my_eyes.jpg (27.7 KB)

>>109003199
>esta hermoso
>si
>te cacho
you illiterate ngroid

google translate is a function x -> emdash for all x

>>109003199
Yes and apart from some pathological cases, it seems to work better for it. It's been performing way better at translating casual posts that contain idioms, slang, and misspellings.

>>109003310
Jewgle is completely jeeted and broken now.
I search verbatim text from reasonably popular sites and it can't find shit other search engines find easily.

>>109003199
transformer was literally invented for google translate..
it's been like a year since they used smaller repurposed gemini

>>109003382
i think so. i couldn't make sense of a certain piece of text when i used yandex translate, so i plugged it into a chatbot and it gave a good translation which was pretty accurate and didn't read like a literal translation

>>109003802
Google's moat is its infrastructure (and the fact that now other services like cloudflare gatekeep most of the internet against bots) but if they break their service too much, someone else can always take the lead in search. Seems unthinkable now, but those are things that happen if a company loses its way too much. The bigger question would be whether most people prefer regular search or those AI summaries.

I should look into that AI manga translator again. Surely they have local LLMs working by now...

>>109004055
Yes, and GPT-image-2 or Nano-Bana-2 can likely make the translation fit in the pages in an acceptable way. It is still recommended to first have a better model translate and just use those for text insertion though.

>>109004128
The tool already does text extraction and typesetting well enough, the only thing missing was decent translation. I was hoping LLMs would do better.
The tool probably can't feed images to the translation model though and japanese relies a lot on context so idk if it'd be good.

>>109004151
Gemini is more than likely a better translator than Google Translate. Feed the page to Gemini Pro.

>>109004151
>>109004162
To continue, most frontier LLMs have vision now. Some local ones do too. You'll want to give good instructions, but you don't even need to extract the text beforehand. If you ask a current LLM to OCR a full page of text, it would likely give sub par results, but for the amount of text that's on a manga page it should be more than able to do that perfectly fine.

>>109004170
That's nice to know. The tool I mentioned (manga-image-translator) hasn't been update in a year, so it's not likely to have gained any significant features since I last used it.
I would still prefer something fully automatic and local though so I guess I'll just wait lol.

File: gemini.png (502.5 KB)

>>109004190
It is pretty automatic. Here is with a random image from https://global.discourse-cdn.com/wanikanicommunity/original/4X/d/f/3/df3ad7cc55b6398b6c1b5da53580d946e734e0e7.jpeg

You'd have to build a pipeline and work on the prompt a bit so that it doesn't feel the need to preface with anything, etc., but it seems to work to me.

File: random_image.jpg (184.1 KB)

>>109004190
>>109004224
Source image

File: random_image_translation.png (1.5 MB)

>>109004190
>>109004224
Translation

>>109004231
pretty dogshit
western ai hates rtl comics. they do not understand manga and it is very hard to make them understand.

>>109004229
>>109004231
>見えないのなら | これではどうだ?
>If you cannot see it... How about *this*? | If you cannot see it
Perfect for gorgeous looks, can push asap.

>>109004235
>>109004237
Might be. I don't speak moon runes. The images models are no good for translation I guess, so what was said here >>109004170 regarding that it's better to have a smarter model translate first seems to stand. I still think they're neat for text insertion. The SHWACK and the DA might be dumb, but it's still cool.

File: random_image_translation_two_steps.png (934.3 KB)

>>109004235
>>109004237
Here it is again asking the model to translate it first and only insert the translation after. Don't know if it's better or worse but it's different.

>>109004248
You can tell from >>109004237 that the translation doesn't make much sense. As a matter of fact it should be
>見えないのなら/If you cannot see it
>これではどうだ?/How about *this*?
the reason it fucks up here, I happen to know, is because it hates when comics are rtl not ltr
>>109004276
same fundamental fuck up: it does the lines ltr instead of rtl. I was trying to coerce gemma4 to give me the correct panel order for a manga page and it couldn't. A larger model should be able to do it but I can see it struggling here.

>>109004055
https://github.com/zyddnys/manga-image-translator
This one? I could never get it working myself.

>>109003382
even with bullshit models you can get pretty ok translations, much, much, much better than something like tesseract. ive translated a couple of german and french academic texts with gemmatranslate:12b and they seem pretty good but still require a lot of manual review

>>109003254
with this we can finally understand wingdings

>>109004589
I got to work after downloading 15GB of libraries, but since it cannot handle context a lot of the translation ended up nonsensical.
Then I updated python and it stopped working.

File: Screenshot From 2025-05-06.png (105.6 KB)

Speaking of gemma

>>109003199
So Yandex translate it is.

>>109004738
Gemma 4 thought the Canadian penny "was retired" in 2034 lol