30 comments

[ 3.3 ms ] story [ 56.3 ms ] thread
I find that meta’s translations are very poor compared to others, at least for relatively obscure languages, which I figured was relevant considering the article.

Google Translate is a good default, but LLMs are really good at translations, as they’re better capable at understanding context and providing culturally appropriate translations.

(I live in Cambodia where they speak Khmer)

That's a high count, but still a bit away from "Omni". Usual count is between 4k and 8k depending the source. But the first 1k might be the hardest, certainly.
1.6k languages is for how many we were able to find more or less reliable evaluation data (mostly thanks to Bible translators and all those who contributed to BOUQuET). Out of the remaining several thousand languages, we expect the OMT models to support understanding (but not generation) for a significant proportion, due to cross-lingual generalisation between similar languages. So it’s not truly “omni” in the sense of supporting every single language on Earth, but it’s our best effort to do so, and probably the most “omni” models existing today.
Is there interest in benchmarking the proprietary LLMs for translation? Curious as I often use Gemini 3 Flash, but I have no idea how good it is for my language family. I prefer open models (in fact the smaller the better for offline), but it'd be useful to know how well the Big Three do.
Off topic, since the AI craze MS‘ documentation translation has ridiculous errors like translating try catch keywords to "versuchen" and "fangen" for German pages
I’m very wary of celebrating Meta’s language work when the company was credibly found to have contributed to the genocide against the Rohingya in Myanmar, and separately, to human rights abuses against Tigrayans during the conflict in northern Ethiopia. Be careful whose sins you’re laundering.

https://www.amnesty.org/en/latest/news/2025/02/meta-new-poli... https://www.amnesty.org/en/latest/news/2023/10/meta-failure-...

I had the same reaction to this post. Mainly because one of Meta's explanations for the lapse was that they didn't have moderators who understood the local language

You hear that folks? Lack of localization kills.

They can translate 1600 languages, but they cannot do basic text formatting, where are the paragraphs?
Just spent a long time trying to find where you can download any of these weights.

Is it open weight? If so, why isn't there just a straight link to the models?

It is not open weight as of today (unfortunately, for the reasons out of control of us the authors, we weren’t able to release the weights). All we could release is part of the evaluation data. I hope this will change in a while.
I'll be looking at this in detail. I've started a company to do similar things, https://6k.ai

I'm currently concentrating on better data gathering for low-resource languages.

When you look in detail at data like Common Crawl, finepdfs, and fineweb, (1) they are really lacking quality data sources if you know where to look, and (2) the sources they have are not processed "finely" enough (e.g. finepdfs classify each page of PDF as having a specific language, where-as many language learning sources have language pairs, etc.

Common Crawl has been running a low-resource language project for 1.5 years now -- it's a hard problem.
Hey, this is super cool! I’ve been working on a similar problem, focusing on low-resource and underserved languages including the Mayan family, and have published some research and open resources around that [0, 1].

On the data side, I’ve found that the biggest bottleneck isn’t collecting text (it’s out there!) but reliable language identification. It’s often difficult or ambiguous to separate languages cleanly in datasets like Common Crawl, Fineweb, or others. I worked on improving this a bit for Fineweb 2 for my native language, that might inspire you [3].

Many of the challenges you mention seem to recur across regions and language families, so I’d love to connect and compare notes sometime. Feel free to reach me at omar [at] the labs site below.

0: https://wikilangs.org

1: https://omneitylabs.com

2: https://huggingface.co/blog/omarkamali/gherbal-multilingual-...

It's sad that I didn't see any languages on your website from Australia, where there are hundreds of languages that need translating.
It’s a small sample and not specifically ones we’re working on. It’s biased towards alternative scripts for visual interest.

Australian languages are definitely interesting! and I will say, from what I’ve seen, Australian government (and other orgs) have done better than most to help document them (in recent years, at least)

Meta released No Language Left Behind (NLLB) [1], I think in 2022. I wonder why this in not "NLLB 2.0"? These companies love introducing new names to confuse things

[1] https://ai.meta.com/research/no-language-left-behind/

This project is absolutely NLLB 2.0 in spirit. However, we decided to reserve the name “OMT-NLLB” only to the subset of the new models that have encoder-decoder architecture similar to the original NLLB-200. The other models are called “OMT-LLaMA” and have classical LLM architecture. The idea here (and we had to emphasize it to justify the project internally) is that we are developing not just new models but a recipe for massive multilinguality that can be integrated into general-purpose LLMs.
Didn’t research show that models get worse at translation the more languages get added in? The curse of multilinguality? Lauscher 2020?

It looks like meta found a way forward.

Reading meta’s abstract, it seems that they have found ways to improve the quality of the training data, and also new evaluation tools?

They are also saying that OMT-LLaMA does a better job at text generation than other baseline models.

Can translate between 1600 languages.

Can't achieve subject-verb agreement in 1st sentence of their English abstract.

Advances made through No Language Left Behind (NLLB) have demonstrated that high-quality machine translation (MT) scale to 200 languages.

Huh? I'm a native English speaker and the sentence looks OK.

Advances have demonstrated... The NLLB part is an adjectival(sic) phrase that modifies the noun "Advances".

Hopefully I'm not wrong...

Where are real, useful features, why in 2026 can't I get transcript of voice messages in my chat?
They've come a long way since enabling Burmese genocide citing lack of available translations.
It can't even do decent Welsh to English translations.