Here you can find various modules (coded in python) used to build SAHYA
Using the face_recognition library Sahya is able to finely recognize the people present in her dataset and greet them using text_to_speech module.
- face_recognition
- cv2
- os
make sure you have the specified libraries installed to run the text_to_speech module which is mentioned in thespeech
folder.
Using the YOLO algorithm,(You only look once) which is an object detection system targeted for real-time processing, Sahya is able to detect objects using the pre-trained data.
ย ย ย ย ย ย kindly look into the setup.md
file for running the code smoothly
This folder consists of python codes to perform Text_to_Speech
and Speech_to_Text
operations.
Text to Speech :
Speech to Text :
This code divides the live streaming into three different screens which shows the the Left, Center and Right perspective views.
Hearty thanks to all the coders and developers for their knowledge, help and support
made with โค๏ธ ๐ฉ๐ปโ๐ป ๐จ๐ฝโ๐ป