|
|
--- |
|
|
title: Part 1 |
|
|
emoji: 🚀 |
|
|
colorFrom: indigo |
|
|
colorTo: indigo |
|
|
sdk: gradio |
|
|
sdk_version: 5.18.0 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: apache-2.0 |
|
|
short_description: Fainal Project , Part 1 |
|
|
--- |
|
|
# AI Study Summary |
|
|
|
|
|
This is a simple text summarization tool built using the `mT5` multilingual model for summarizing text in both Arabic and English. It uses the Hugging Face `transformers` library and Gradio to create an interactive web interface for summarizing text input. |
|
|
|
|
|
## Features |
|
|
|
|
|
- Summarize text in multiple languages, including Arabic and English. |
|
|
- Use a pre-trained multilingual summarization model (`csebuetnlp/mT5_multilingual_XLSum`). |
|
|
- Simple, user-friendly Gradio interface to input text and receive summaries. |
|
|
|
|
|
## How It Works |
|
|
|
|
|
The application uses a pre-trained model called `mT5_multilingual_XLSum` for text summarization. The user can enter text in Arabic or English, and the model will generate a concise summary of the input. |
|
|
|
|
|
### Example Texts |
|
|
|
|
|
- Arabic: |
|
|
> "الذكاء الاصطناعي هو فرع من علوم الكمبيوتر يهدف إلى إنشاء آلات ذكية تعمل وتتفاعل مثل البشر. بعض الأنشطة التي صممت أجهزة الكمبيوتر الذكية للقيام بها تشمل: التعرف على الصوت، التعلم، التخطيط، وحل المشاكل." |
|
|
|
|
|
- English: |
|
|
> "Artificial intelligence is a branch of computer science that aims to create intelligent machines that work and react like humans. Some of the activities computers with artificial intelligence are designed for include: Speech recognition, learning, planning, and problem-solving." |
|
|
|
|
|
## Requirements |
|
|
|
|
|
To run this project locally, you need Python 3.7 or higher. Additionally, you need to install the following Python libraries: |
|
|
|
|
|
- pip install gradio. |
|
|
- pip install transformers. |
|
|
|
|
|
--- |
|
|
|
|
|
- Gradio: Provides a simple interface for building and sharing machine learning demos. |
|
|
- Transformers: Hugging Face's library for pre-trained models, in this case, for multilingual text summarization. |
|
|
- Torch: PyTorch is used as the backend for the model. |
|
|
|
|
|
|
|
|
## How to Run Locally |
|
|
- Clone the repository or download the app.py and requirements.txt files. |
|
|
- Create a virtual environment and activate it (optional but recommended). |
|
|
|
|
|
- Install the required libraries by running: |
|
|
|
|
|
pip install -r requirements.txt |
|
|
|
|
|
- Run the application: |
|
|
- |
|
|
python app.py |
|
|
## How It Works |
|
|
- The Gradio interface allows you to input text and select the language (Arabic or English). |
|
|
- The model will generate a summary of the text based on the language selected. |
|
|
- You can also use pre-defined example texts to quickly test the summarization feature. |
|
|
|
|
|
Input: |
|
|
- Text: "Artificial intelligence is a branch of computer science that aims to create intelligent machines that work and react like humans." |
|
|
- Language: English |
|
|
|
|
|
Output: |
|
|
- Summary: "AI is a branch of computer science aimed at creating intelligent machines that mimic human behavior." |
|
|
|
|
|
## License |
|
|
This project is licensed under the MIT License - see the LICENSE file for details. |
|
|
|
|
|
## Acknowledgements |
|
|
The summarization model used in this application is based on the mT5 Multilingual XLSum model by Hugging Face and is fine-tuned on the XLSum dataset for summarization in multiple languages. |
|
|
Gradio is used to build the web interface, making it easy to interact with the model. |
|
|
|
