The website is intended towards optimization of resource management in laboratory of educational institutions. Built with React for frontend and Django for backend. The website includes Face authentication based admin page verification, voice based entity querying and scanned invoice data entry into database without manual form entry.
- google flan t5 : https://huggingface.co/google/flan-t5-large/
- vosk : https://alphacephei.com/vosk/models/vosk-model-small-en-in-0.4.zip
- cnn model for face regonition : https://github.com/jomariya23156/face-recognition-with-liveness-web-login/tree/master/face_recognition_and_liveness
create a directory in the root folder of the backend called local_models and drop all three models in that directory. Nvidia GPU with cuda-toolkit recommended for better performance.