Emotional Detection using Bidirectional Encoder Representations from Transformers (BERT).
Using ED-BERT, you can:
- Detect emotion from text.
- Report incorrect prediction and save the data on database.
- Train your own model with additional data from database.
- Python 3.10 or higher
- Streamlit 1.25.0 or higher
- MySQL 8.0.32 or higher
- Docker 24.0.4 or higher (optional)
- docker-compose 1.29.2 or higher (optional)
- Clone the repository
git clone https://github.com/putuwaw/ed-bert.git
- Create virtual environment and activate it
python -m venv venv
source venv/bin/activate
- Install the dependencies
pip install -r requirements.txt
-
Set up database using SQL dump in init.sql file.
-
Run the app
streamlit run Home.py
Important
This repository contain .h5 file which is the model of ED-BERT. Please consider to read about Git Large File Storage.
- Clone the repository
git clone https://github.com/putuwaw/ed-bert.git
- Run the app
docker-compose up
This project is licensed under the MIT License. See the LICENSE file for details.