firefox-translations

Interestingly, I think this is actually related to the offline translation features built into Firefox. Both are products of "Project Bergamot", but the Mozilla-maintained version was later merged into the Firefox application: https://browser.mt/ https://blog.mozilla.org/en/mozilla/local-translation-add-on... https://hacks.mozilla.org/2022/06/training-efficient-neural-... https://github.com/mozilla/firefox-translations https://firefox-source-docs.mozilla.org/toolkit/components/t... Extra webpage with screenshot and links, impossible to search for normally: https://translatelocally.com/downloads/ Does one thing and does it well. Oh— For downloading models, it's much easier to pipe/`xargs` `translateLocally --available-models` into `translateLocally -d` than go through the GUI. --- Other self-hostable translation tools: https://www.apertium

Mozilla did release DeepSpeech[0] and Firefox Translation[1] (the latter of which they included in Firefox, to offer client-side webpage translations.) They definitely have fewer resources than OpenAI, and they do not produce SOTA research (their publications have plummeted to 1/year anyway[2]). So the only way for them to make progress is to seek government grants or make challenges like these. This challenge is unlikely to be profitable for the winning team: the expected value of winnings are likely around $1K when taking into account the probability that another team gets a better rank, but ML research projects are often more expensive (recently, Alpaca spent upwards of $600 on computation alone; and of course pretraining large models is much more expensive). So the main gain will be publicity. [0]: https://github.com/mozilla/deepspeec

Models are downloaded only once and then cached, and not repeatedly like the OP mentioned. Source: Me. I've developed it. If you disagree, are seeing a different behavior or have further questions, please reach out in the repo: github.com/mozilla/firefox-translations/

https://github.com/mozilla/firefox-translations/issues/374 Maybe it will get implemented

DOM changes should be handled and it should be working still. Could you please file a bug https://github.com/mozilla/firefox-translations/issues with the proper steps to reproduce, please?

> The first release translated endless twitter scroll inline perfectly. This is the right behavior and it's still working for me. Could you please file an issue to: https://github.com/mozilla/firefox-translations/issues with your STRs?

previous discussion here: https://news.ycombinator.com/item?id=31596888 as noted in [0], the models are hosted on storage.googleapis.com and downloaded on demand. this still seems to be the case [1] 0: https://news.ycombinator.com/item?id=31604095 1: https://github.com/mozilla/firefox-translations/blob/main/ex...

click the link that says "Support site" https://github.com/mozilla/firefox-translations

Maybe you can develop it, if you want. The models and the source code for running it are all there, someone just have to wrap it in a standalone binary instead of a WebExtension. - https://github.com/mozilla/firefox-translations - https://github.com/mozilla/firefox-translations-models - https://github.com/mozilla/bergamot-translator Note that most of the heavy NLP code used (MarianMMT, fasttext) were originally written as C++ libraries but were compiled to WebAssembly to make a WebExtension out of it. So if you want to make a command line / GUI desktop app there are two choices: use C++ directly if you want to make an app with minimal dependencies, or use JS/WebAssembly to make a NodeJS / Electron based app (which might be heavier but more accessible for JS devleopers.)

Thanks for using it! Best way currently is to keep using and reporting issues on [1]. You can see how the models are trained on [2] and file issues there too. [1] https://github.com/mozilla/firefox-translations/issues [2] https://github.com/mozilla/firefox-translations-training

Another user has posted a link to that issue: https://github.com/mozilla/firefox-translations/issues/358. I upvoted it instead of creating a new one.

Yes, like I said above that's something we've been discussing internally and is being considered. In this meantime, please feel free to file an issue in the repo [1] so we could track it: [1] https://github.com/mozilla/firefox-translations/issues

Yes, that's something we've been discussing internally and is being considered. In this meantime, please feel free to file an issue in the repo [1] so we could track it: [1] https://github.com/mozilla/firefox-translations/issues

> Are there any plans for Mozilla to host this data? (Well, Amazon I guess to match addons.mozilla.org) I'll bring this internally for discussion. > I noticed the web page has Polish but not the extension. Is it not considered sufficiently high quality yet? (Looks like that might be the case from a quick test.) The Polish model finished training after we had the extension reviewed and signed for distribution, so that's why we could already integrate it in the website, which is controlled just by my team, and not in the extension yet, but we'll ship it in the next version which might come next week. This feature you requested is something that I consider interesting and important, would you mind filing an issue in the repo so we could track it [1]? We did not find any large quality issues after quantizing the models. In regards to the neo