Who it is forA developer or agent that needs to translate a list of Bosnian sentences into English for a dataset or report.
The problemTranslating many lines by hand in the web page takes too long and cannot be repeated.
The outcomeA file of English translations produced from a list of Bosnian lines.
What you need first
- Python 3.12 and uv for the local install, or a browser for the live demo
- Internet access for the first model fetch; the README says nothing reaches the network after fetch_models.py finishes
- Optional: a microphone for speech and a camera for photographs
Steps
- Create the environment:
uv venv .venv --python 3.12 - Install the dependencies:
uv pip install --python .venv/bin/python -r requirements.txt - Fetch the models:
.venv/bin/python scripts/fetch_models.py - Write a script that reads each Bosnian line from your input file and calls
lilly.translate(line)fromapp.lilly(inferred, check the README) - Run the script with
.venv/bin/pythonand write each result next to its source line (inferred, check the README)
Prompt for your agent
In the repo ssaaffaakk/Lilly, use the Python object lilly from app.lilly to call translate on each line of <input file>. Expected output: one English line per Bosnian input line, saved to <output file>. Verify that the line counts of input and output match before reporting.
Caveat. The translator is measured on FLORES-200 sentences, so batch output on other text may vary and should be spot-checked.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page