SpeechPro

Inspiration

The need for inclusive communication tools inspired the creation of SpeechPro. We aimed to bridge the communication gap for individuals using sign language by converting gestures into text and speech.

What it does

SpeechPro allows users to upload images of sign language gestures, which are then converted into text and speech in either English or Hindi. This aids in communication for both deaf and hearing individuals.

How we built it

We used Python, Flask for the backend, TensorFlow/Keras for the gesture recognition model, OpenCV for image processing, and gTTS for text-to-speech conversion. The front end was built with HTML, CSS, and JavaScript.

Challenges we ran into

Handling large datasets, ensuring accurate gesture recognition, and implementing multilingual text-to-speech conversion were significant challenges. Integrating all components seamlessly was also challenging.

Accomplishments that we're proud of

We successfully developed a working prototype that converts sign language gestures into text and speech. The project supports multiple languages and has a user-friendly interface.

What we learned

We learned about advanced machine learning techniques, the importance of preprocessing data, and the complexities of integrating various technologies to create a cohesive application.

What's next for SpeechPro

Future plans include expanding the gesture dataset, improving the accuracy of gesture recognition, adding support for more languages, and deploying the application for broader accessibility.

Built With

• css
• javascript
• python-flask-tensorflow/keras-opencv-gtts-(google-text-to-speech)-html