Levanti - Levantine Arabic Translation Tools

Levanti - Levantine Arabic Translation Tools

Translates text between English and Levantine Arabic, adds vowel marks to Arabic and writes it in Latin letters. Runs in the browser for learners, translators and anyone working with the dialect.

Made by guymorlan on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Levanti is a small web app for working with Levantine Arabic. It translates in both directions between English and the dialect, and it can add vowel marks to Arabic text and write it out in Latin letters.

Four models do the work, each with one job: two translate (one per direction), one adds the vowel marks and one produces the Latin spelling. The Space also names a dataset called levanti.

Who it suits: People who read, learn or translate Levantine Arabic and want a quick way to move between the dialect and English.

Industry | Who uses it | How they use it | Example
Education | Arabic learners | Read dialect text with vowel marks and a Latin spelling | Look up a phrase from a conversation
Translation | Translators | Draft a sentence in either direction and compare it with their own | Check an English line against the Arabic output
Research | Language researchers | Try sentences on a dialect translation model | Test short sentences in both directions

You can skip it if all your Arabic work is in standard written Arabic.

Where to use it:

• A web browser, on the Space's page at Hugging Face, with nothing to install
• Windows, macOS or Linux with Python, from a copy you download

Use case | Who | What they get back
Translate a sentence | Learners and translators | English or Levantine Arabic text
Add vowel marks | Readers of Arabic | The same Arabic text with diacritics
Write in Latin letters | Beginners | The Arabic text spelled with Latin characters

How to set it up:

• Python on your computer
• The Python packages listed in requirements.txt
• The huggingface_hub package, which gives you the hf command

1. Install the huggingface_hub package.
2. Download the Space with the hf command.
3. Move into the downloaded folder.
4. Install the pinned Gradio version.
5. Install the packages from requirements.txt.
6. Start the app with Python.

pip install -U huggingface_hub
hf download guymorlan/levanti_en_ar --repo-type space --local-dir levanti_en_ar
cd levanti_en_ar
pip install gradio==4.38.1
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page in your browser, or run the app from your own copy with the command below. Then enter a sentence in English or Levantine Arabic and read what the app returns.

python app.py

Example: You type a short English greeting and ask for Levantine Arabic. The English to Arabic model returns the Arabic text, and the other models can add vowel marks to it and a Latin spelling.

For newcomers and experts: If you are new to the dialect, open the page and try one short sentence in English. Look at the Arabic that comes back, then compare it with its Latin spelling to see how the letters map to sounds.

If you know the field, note that the app chains separate models instead of one system. The repository keeps a folder for each translation direction, with Python files for diacritics, transliteration, translation and more. The Space runs on basic CPU hardware at Hugging Face.

You enter text on the page
app.py sends it to a model
Translation or vowel marks are added
The result shows on the page

Good to know:

• License: the Space lists cc-by-nc-4
• Cost to run: none named
• Data it reaches: the text you enter, plus the files in the Space
• Not for: commercial use is likely off the table with a non-commercial license, so check its terms first

On Hugging Face, 13 November 2026

• Likes: 12
• Built with: gradio
• License: cc-by-nc-4.0

Links

• Space: https://huggingface.co/spaces/guymorlan/levanti_en_ar
• Files: https://huggingface.co/spaces/guymorlan/levanti_en_ar/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.