Text_summarization_with MBART(50 Languages)

Text_summarization_with MBART(50 Languages)

A Gradio app that summarises text with Facebook's mBART large 50 model, which covers 50 languages. Suits people who want to try multilingual summarising in a browser.

Made by Sultannn 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: This Space is a Gradio app for text summarisation built on facebook/mbart-large-50, a multilingual model. Its title says it handles 50 languages. The repository is only three files, so the app is a thin page around that one model. The page has no description, so the exact controls are not confirmed.

Who it suits: Anyone who wants to try summarising text in many languages, and developers who want a short example of a translation model used inside Gradio.

Industry | Who uses it | How they use it | Example
Education | Students and teachers | Shorten a reading passage in their own language | Paste a long paragraph and read the short version
Software | Developers | Use the project as a pattern for a Gradio summariser | Swap in a different model name
Research | Language researchers | Try one multilingual model on sample texts | Compare outputs across languages

Skip it if you need summaries you can rely on without checking, because a model can leave out or distort details.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• Windows, macOS or Linux with Python, from a downloaded copy

Use case | Who | What they get back
Summarise a text online | Anyone curious | A shorter version of the text you give it
Read a small summariser demo | Developers | A three file Python project to study

How to set it up:

• Nothing to install for the online version
• Python on your computer for a local copy
• The packages listed in requirements.txt

1. Install the Hugging Face hub package.
2. Download the Space's files to a folder.
3. Move into that folder.
4. Install gradio, then the packages from requirements.txt.
5. Start the app with app.py.

pip install -U huggingface_hub
hf download Sultannn/Text_summarization_with-MBART --repo-type space --local-dir Text_summarization_with-MBART
cd Text_summarization_with-MBART
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Open the Space page in a browser, paste or type the text you want shortened and submit it. For a local copy, run the app and open the page Gradio opens for you.

python app.py

Tool | What it does
python app.py | Starts the Gradio app on your computer
hf download | Copies the Space's files into a local folder

Example: Paste a long news paragraph into the text box and submit it. The app should return a shorter summary written by the mBART model. The page does not list the settings, so use what it shows.

For newcomers and experts: If you are new to this, paste a paragraph you know well and see whether the short version keeps the main point. Then try a different language.

If you know the field, the app names a single model, facebook/mbart-large-50. The page gives no generation settings, length limits or evaluation scores, so treat its output as a demo result.

You paste a text
The mBART model reads it
It writes a shorter version
Gradio shows the summary

Good to know:

• The page lists no length limits or quality scores.
• The online version needs nothing installed, and a local copy needs Python.
• License: apache-2.
• Cost to run: none named, only the packages in requirements.txt.
• Data it reaches: the text you submit. On the hosted Space, that text is handled on Hugging Face. A local copy downloads the model from there.
• Not for: the source names none. Check any summary against the original before you rely on it.

On Hugging Face, 13 November 2026

• Likes: 2
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/Sultannn/Text_summarization_with-MBART
• Files: https://huggingface.co/spaces/Sultannn/Text_summarization_with-MBART/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.