Ancient Library – 1,060 Greek/Latin texts, click any word to parse it(ancientlibrary.net) |
Ancient Library – 1,060 Greek/Latin texts, click any word to parse it(ancientlibrary.net) |
I built something similar to this by cloning the Diogenes repo and getting Claude to re-implement it in Python (it’s a very old battle tested Perl code base, so a great reference implementation) and using the TLG database for the Greek and Latin texts. You can take this even further by integrating it with the Barrington Atlas (there are scans on Anna’s Archive) for looking up ancient place names, so you have dictionary + map lookups. If you’ve read any of the Landmark series books you’d known what I mean.
Also better if you can generate chapter by chapter critical apparatus on difficult grammar and Anki decks. It’s an annoying part of learning these languages to have to stop and look up words, I like spending a few days learning vocab before reading and it makes it so much more pleasant than having to stop and look things up the whole time.
Obviously all this stuff is copyright so it can never be shared, but I don’t care it’s for my own personal use. I also bought like 6 hours worth of Ionnis Strattakis’ recordings where he reads a bunch of Ancient Greek in reconstructed Attic pronunciation and fine-tuned a text to speech model (styletts2) with full accent markings and breathings. It’s extremely natural sounding. My long term goal is to have a personal tutor that I can speak Attic to and basically have lessons with everyday (speech to text -> llm-> text to speech). All the pieces are there to actually do this.
LLMs have been an absolute game changer for me who is a hobby classicist but also knows how to build software. They are so amazingly good at Attic Greek and Latin, it’s like having the best teachers in the word at your fingertips for some really niche topics that it wouldn’t be possible with otherwise. Also extremely good at managing, building, cleaning up, deduplicating Anki decks.
Definitely! I myself have been having a lot of fun[0] recently using LLMs to enrich one of my favorite beginner Latin readers[1] with audio forced-alignment, POS tagging, morphology, definitions, and other niceties that learners might appreciate.
[0]: https://hercules.hookbangsplat.com
[1]: https://archive.org/details/p1fablesoforbili00godl/mode/2up
Also most of the word popups use different spellings, like "iam" becomes "jam".
I don't get a definition for 'fulgere', third word first entence, just a reference to 'fulgo'. I can guess what it means though from the more common 'fulgur', maybe something adjacent to flashing or lightning, but translations seem a bit sketchy.
It seems some books are missing chapter markings. Revelation, for instance. The verses are numbered, and you can notice when chapters change, but one can be lost when searching for a specific chapter.
Dictionary entries are cool, but I would want the in context meaning at least highlighted, so I don't have to read the full entry and do that myself.
Overall, nice idea but it seems like a very barebones implementation that needs a tremendous amount of polishing to be useful.
One parses phrases, sentences, and lines of code.