Yosef-ft/Amharic_NER

Fine-tuning LLM’s for Amharic Named Entity Recognition (NER) system that extracts key business entities such as product names, prices, and Locations, from text shared across Telegram channels. # Telegram E-Commerce NER Project This project aims to establish a centralized platform for Telegram-based e-commerce activities in Ethiopia. With the growing popularity of Telegram for business transactions, various independent e-commerce channels have emerged, each operating separately. This decentralization creates challenges for both vendors and customers, who must navigate multiple channels for product discovery, order placement, and communication. To address these challenges, the project focuses on developing a Named Entity Recognition (NER) system specifically designed for the Amharic language. The NER system will extract key business entities, such as product names, prices, and locations, from text, images, and documents shared across multiple Telegram channels. The extracted data will be used to populate a centralized database, transforming the user experience by providing a unified platform for exploring and interacting with various vendors. ## Project Goals - Create a unified platform for exploring multiple e-commerce Telegram channels. - Implement a robust NER system to extract essential business entities from messages. - Enhance the customer experience by consolidating real-time data into a single channel. ## Getting Started ### Prerequisites Make sure you have the following installed: * Python 3.x * Pip (Python package manager) ### Running notebooks: - It is better to run the notebooks on Colab ### Installation Clone the repository: ``` git clone github.com cd Amharic_NER ``` Create a virtual environment and activate it: ``` python -m venv venv source venv/bin/activate # On Windows use `venv\Scripts\activate` ``` Install the required packages: ``` pip install -r requirements.txt ```