This project focuses on developing a tool that translates spoken English into Indian Sign Language (ISL) using real-time speech recognition and text-to-sign language conversion. The application captures audio from a microphone, transcribes it to text, and then converts the text to sign language animations or letter-by-letter images.
Name: Mrinank Kavuri
Email: [email protected]
LinkedIn: Mrinank Kavuri
- Objective: Convert spoken English into ISL and vice versa to bridge communication gaps for the deaf community.
- Technologies Used:
- Speech Recognition:
speech_recognition
library - Text Processing: Python string operations
- Image Handling:
PIL
(Python Imaging Library) - GUI:
Tkinter
for displaying GIFs,matplotlib
for letter images - Data Storage: MP4 video files and image files
- Speech Recognition:
- Dependencies:
numpy
matplotlib
PIL
(Pillow)tkinter
speech_recognition
- Real-time Audio Capture: Listens to and captures audio from the microphone.
- Speech-to-Text Conversion: Transcribes the captured audio to text.
- ISL Translation: Converts the transcribed text into ISL using GIF animations for predefined phrases or letter-by-letter images.
- Error Handling: Manages errors in speech recognition and displays appropriate messages.
- Clone the repository:
git clone https://github.com/mrinank1301/project-language.git
- Install required packages:
pip install numpy matplotlib pillow speechrecognition