What do you want to do?
5 use cases
-
Translate Bosnian text to English on your own machine
Run Lilly locally so Bosnian text is translated with no internet after the model fetch.
- Lilly
- Work and operations
- Intermediate
View prompt
In the repo ssaaffaakk/Lilly, set up the local app with the README steps, then translate the Bosnian sentence <bosnian sentence> through lilly.translate or POST /api/translate. Expected output: the English text returned by the app. Verify that the server answers on http://localhost:8000 before reporting the translation.
-
Read a Bosnian sign or whiteboard from a photo
Point a camera at a sign and see its English translation drawn over the photo.
- Lilly
- Work and operations
- Beginner
View prompt
Using the live Lilly demo at safak11-lilly-api.hf.space from the ssaaffaakk/Lilly repo, submit a photo of <sign image> to the photo reading flow. Expected output: the sign text and its English translation, one per region. Verify that the regions match the visible text in the photo before reporting.
-
Translate a Bosnian .docx or PDF file to English
Upload a Word or PDF file and get its text translated sentence by sentence.
- Lilly
- Work and operations
- Intermediate
View prompt
In the repo ssaaffaakk/Lilly, set up the app with the README steps, then send the file <document path> to POST /api/document. Expected output: the extracted and translated text. Verify that the number of translated sentences is close to the number of sentences in the source file.
-
Speak English and hear the Bosnian reply
Talk in English, get the Bosnian reply, and hear it read aloud in Bosnian.
- Lilly
- Work and operations
- Intermediate
View prompt
In the repo ssaaffaakk/Lilly, confirm that translator-en-bs/ and speak-bs/ exist after setup, then call POST /api/reply with the English text <english sentence>. Expected output: the Bosnian reply text. Verify that /api/speak with language bs returns WAV audio rather than a 503.
-
Batch-translate a folder of Bosnian text with the Python API
Call Lilly's Python object from a script to translate many Bosnian lines in one run.
- Lilly
- Work and operations
- Advanced
View prompt
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.
How to use Lilly
- Check you have what it needs: 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.
- Open ssaaffaakk/Lilly on GitHub and read the README and license.
- 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 - Start the server:
.venv/bin/uvicorn app.server:app --port 8000
These steps come from our top use case, Translate Bosnian text to English on your own machine, which also has a copy-paste agent prompt.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forWritten for people who need to follow or answer Bosnian speech, signs, or documents without knowing the language, and for agents that will run the local setup.
- Why it is hot
- LanguagePython
- Sourcegithub.com/ssaaffaakk/Lilly · Back to Hot repos
Requirements
- 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
Add this badge to your README
Maintain Lilly? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/ssaaffaakk-lilly/?utm_source=github&utm_medium=badge&utm_campaign=ssaaffaakk-Lilly)
HTML
<a href="https://dedupedai.com/use-cases/ssaaffaakk-lilly/?utm_source=github&utm_medium=badge&utm_campaign=ssaaffaakk-Lilly"><img src="https://dedupedai.com/badge/ssaaffaakk/Lilly.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Lilly
What is Lilly?
Lilly is an offline Bosnian to English translator with a web app that also handles typed English-to-Bosnian replies, speech, photographs, and documents. It is an open-source project on GitHub: https://github.com/ssaaffaakk/Lilly.
Who is Lilly for?
Written for people who need to follow or answer Bosnian speech, signs, or documents without knowing the language, and for agents that will run the local setup.
What can I do with Lilly?
5 use cases so far, for example: Translate Bosnian text to English on your own machine; Read a Bosnian sign or whiteboard from a photo; Translate a Bosnian .docx or PDF file to English. Each has steps and a copy-paste agent prompt.
What do I need to run Lilly?
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.
What are alternatives to Lilly?
Other hot AI repos in Work and operations: Spynel, Agents Office, Knowledge Work Plugins, Itsaplan, Endoplexity.
Is Lilly safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.