Abdu1964/Amharic-hatespeech-detection-With-API

Amharic Hate Speech Detection with Streamlit --------------------------------------------------- Overview This application uses a Hugging Face model to detect hate speech in Amharic text. It provides a simple and interactive web interface powered by Streamlit, allowing users to input text and receive predictions on whether the text contains hate speech or not. Features Simple UI for users to input text. Real-time classification using a Hugging Face model (abdaiyan/amharic-hate-detection). Outputs predictions with confidence scores. Accessible through any web browser. Installation and Setup Requirements ------------------- Python 3.9 or later (ensure compatibility with the packages listed in requirements.txt). The following Python libraries: streamlit transformers torch Steps to Set Up Locally Clone the Repository git clone github.com / .git cd Set Up a Virtual Environment python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate Install Dependencies Use the requirements.txt file to install the necessary packages. pip install -r requirements.txt Run the Streamlit App Launch the application locally. streamlit run app.py Access the App Open your browser and go to: arduino Copy code localhost Files in the Repository 1. app.py The main application file: Imports necessary libraries (streamlit, transformers). Loads the pre-trained Hugging Face model for Amharic hate speech detection. Provides a user interface for inputting text and displays predictions. 2. requirements.txt Contains the dependencies needed to run the app streamlit transformers torch How It Works User Input: Users can input Amharic text in the text area provided by the Streamlit app. Model Prediction: The app uses the Hugging Face pipeline for text-classification, loading the abdaiyan/amharic-hate-detection model. The model predicts whether the text is hate speech or not hate speech, along with a confidence score. Result Display: The app displays the pr …