this post was submitted on 24 Apr 2024
52 points (98.1% liked)

Selfhosted

39232 readers
332 users here now

A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.

Rules:

  1. Be civil: we're here to support and learn from one another. Insults won't be tolerated. Flame wars are frowned upon.

  2. No spam posting.

  3. Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it's not obvious why your post topic revolves around selfhosting, please include details to make it clear.

  4. Don't duplicate the full text of your blog or github here. Just post the link for folks to click.

  5. Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).

  6. No trolling.

Resources:

Any issues on the community? Report it using the report flag.

Questions? DM the mods!

founded 1 year ago
MODERATORS
 

I am a teacher and have students who speak many different languages. The most common ones are Chinese, Spanish and Portuguese, but we have other folks speaking other languages as well.

I wish to translate all my notes, lecture subtitles, and topic-exercise documents to other languages. Moreover every year, I have to update my teaching material and include new stuff. So, muddling though everything manually is not much of an option as it might take up to two months just for this task.

Are there nice self hosted and libre/open source solutions out there for this task?

all 10 comments
sorted by: hot top controversial new old
[–] [email protected] 20 points 4 months ago (1 children)
[–] [email protected] 11 points 4 months ago

Looks like the engine behind it is https://opennmt.net/

Which can use a Tensor Flow backend, which can potentially be accelerated by a rather cheap Coral TPU. Neat!

[–] [email protected] 13 points 4 months ago (2 children)

Yes, just grab any recent LLM like Mistral-7B and ask it to translate for you. A local client is here https://github.com/LostRuins/koboldcpp but you might need a good GPU to get quick answers.

Alternatively use https://lite.koboldai.net to use someone else's computer.

[–] [email protected] 6 points 4 months ago (3 children)

How trustworthy are LLM translations? Normal machine translation may lose context but I imagine LLM could make up shit?

[–] [email protected] 8 points 4 months ago

All translations are LLM translations by this point I believe.

[–] [email protected] 4 points 4 months ago

Translator here. They do make up stuff or omit stuff they don't like. Machine translation is fine for tourists or to translate a ikea manual in the wrong language. If there are stakes, risky. They got good enough to make sentences that look right so it can be tricky to spot the errors if you don't pay attention.

Numbers are typical errors. Sometimes it's there but the number has changed. Sometimes it's not there at all. Oh and if you have currencies a translators knows a document from the UK in pounds that is adapted for France will have to be converted in euros. Machines don't.

Generally speaking when a client wants to use machine translation, it costs them more money in the end because of the extra time needed to correct everything to a high human grade standard.

[–] [email protected] 2 points 4 months ago

From my experience: They're pretty good

[–] [email protected] 1 points 4 months ago

A simpler answer might be llamafile if you're using Mac or Linux.

If you're on windows you're limited to some smaller LLMs without some work. In my experience the smaller LLMs are still pretty good as chat bots so they might translate well.

[–] [email protected] 3 points 4 months ago

Please add a disclaimer to the documents stating it was machine translated. Machine translation can get it wrong or take liberties, make up stuff. Please inform your readers so they can be on the lookout.

Keep in mind the translated stuff by machine translation won't be 100% what you say in your native language to other students. Be careful not to spread wrong information or knowledge.