---
title: Summarization
emoji: 📝
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 3.50.2
app_file: app.py
pinned: false
license: apache-2.0
---

# Text Summarization Hugging Face Spaces App

Welcome to the Text Summarization Hugging Face Spaces App! This app allows you to generate text titles using the XJLULU/NTU_ADL_SUMMARIZATION_MT5_S model.

## App Description

This app takes a piece of text as input and generates a summary of the text. You can either enter your own text or click the "Random" button to get a random example from a provided dataset and generate a summary.

## How to Use

1. Enter or paste a piece of text into the "Context paragraph" textbox.
2. Click the "Generate" button to generate a summary.
3. You can also click the "Random" button to generate a random example for summarization.

## Example Data

The app uses a dataset of examples provided in the [sample_data.jsonl](https://huggingface.co./spaces/xjlulu/summarization/blob/main/sample_data.jsonl) file. Each example in the dataset contains a "text" field. You can either provide your own text or use the "Random" button to choose an example from the dataset.

## Model Information

This project uses the [xjlulu/ntu_adl_summarization_mt5_s](https://huggingface.co./xjlulu/ntu_adl_summarization_mt5_s) model from Hugging Face.


## Local Setup

If you want to run this app locally, follow these steps:

1. Clone the repository:

    ```python
    git clone https://huggingface.co./spaces/xjlulu/summarization
    ```

2. Navigate to the project directory:
    ```python
    cd summarization
    ```
3. Install the required libraries:

    ```python
    pip install -r requirements.txt
    ```

4. Run the app:

    ```python
    python app.py
    ```

The app will start locally and be accessible at [http://localhost:7860]. You can access it in your web browser.

## Credits

- [Hugging Face Transformers](https://github.com/huggingface/transformers)
- [Gradio](https://gradio.app/)
- [apache-2.0](https://www.apache.org/licenses/LICENSE-2.0)

## License

This project is licensed under the apache-2.0 - see the [apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) file for details.

## Acknowledgments

Thank you to the open-source community for developing the amazing tools and libraries that make this project possible.