Real Time Conversion Of Sign Language To Text and Speech(For Marathi and English)

This report offers an examination of the effectiveness of several methods for translating sign language into text and voice. An application created that can translate real-time sign language to text and speech using the best technique after analysis. The model is made for ASL and marathi sign language. CNN model is used for predicting sign language from images captured from frames using OpenCV. GTTS is used for converting the text output to a sound file then presented as a voice version of text output. Accuracy, precision, recall are used to evaluate the model’s performance. The model achieved 98% accuracy.