MIMOUNI-HICHAM/DARIJA_TO_ENGLISH_TRANSLATOR

A smart Flask-based translator for English Darija ,translate full sentences, auto-correct input, and expand the dataset with user-added phrases in real time. # English to Darija Translator 🇬🇧➡️🇲🇦 A simple yet clever web-based **English to Darija (Moroccan Arabic)** translator built with Flask. ## 🧠 How it Works - Uses a large dataset of English–Darija phrase pairs stored in `dataset.csv`. - Translates full sentences or phrases using a combination of: - Phrase matching - Word-by-word translation - Text correction via `TextBlob` - Learns over time — users can add new phrase pairs through the interface. ## 🖥️ Features - Translate English sentences into Darija. - Add your own phrases to the dataset. - Intelligent matching for multi-word phrases. - Auto-correction for better translation accuracy. ## 🚀 Getting Started ### 1. Clone the repository ```bash git clone github.com cd your-repo-name ``` ### 2. Install dependencies ```bash pip install -r requirements.txt ``` Make sure you also download NLTK's tokenizer data: ```python import nltk nltk.download('punkt') ``` ### 3. Run the app ```bash python app.py ``` Then open your browser at `127.0.0.1`. ## 🗃️ Dataset The translator uses a CSV dataset (`dataset.csv`) where each row is a pair: ``` darija,english ``` Example: ``` labas 3lik,how are you ``` ## 📁 File Structure ``` ├── app.py # Main Flask app ├── last.py # Core translation logic and helper functions ├── dataset.csv # Translation data ├── templates/ │ └── try.html # HTML interface ``` ## 📅 Project Info - **Created:** April 2024 - **Made with ❤️ by HIM7** --- Feel free to contribute or suggest improvements!