ODSR

Object detection and Speech recognition

To run this project install necessary pacakages and libraries .
pip install opencv-python numpy speechrecognition torch pyttsx3
Create an environment in the same folder .
This project can run both online and offline

To run this offline

Add the below line
model = cv2.dnn.readNetFromCaffe("MobileNetSSD_deploy.prototxt.txt", "MobileNetSSD_deploy.caffemodel")
{check the correct location of the file }
In place of
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')

Built With

• python