https://github.com/rhythmusbyte/sign-language-to-speech

Real-time ASL interpreter using OpenCV and TensorFlow/Keras for hand gesture recognition. Features custom hand tracking, image preprocessing, and gesture classification to translate American Sign Language into text and speech output. Built with accessibility in mind.
https://github.com/rhythmusbyte/sign-language-to-speech

asl assistive-technology cv2 hand-tracking handdetection image-classification image-processing keras machine-learning mediapipe numpy opencv python real-time-detection real-time-recognition sign-language tensorflow

Last synced: 6 months ago
JSON representation

Real-time ASL interpreter using OpenCV and TensorFlow/Keras for hand gesture recognition. Features custom hand tracking, image preprocessing, and gesture classification to translate American Sign Language into text and speech output. Built with accessibility in mind.

• Host: GitHub
• URL: https://github.com/rhythmusbyte/sign-language-to-speech
• Owner: RhythmusByte
• License: bsd-3-clause
• Created: 2025-02-06T04:32:57.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-03-30T08:31:01.000Z (6 months ago)
• Last Synced: 2025-04-04T04:46:39.893Z (6 months ago)
• Topics: asl, assistive-technology, cv2, hand-tracking, handdetection, image-classification, image-processing, keras, machine-learning, mediapipe, numpy, opencv, python, real-time-detection, real-time-recognition, sign-language, tensorflow
• Language: Python
• Homepage:
• Size: 1.19 GB
• Stars: 5
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          


[![Typing SVG](https://readme-typing-svg.demolab.com?font=Josefin+Sans&pause=1000&color=9D00FF&center=true&vCenter=true&width=435&lines=Sign+Language+to+Speech+Conversion;Real-time+ASL+Recognition+System)](https://github.com/RhythmusByte/Sign-Language-to-Speech)



[![License](https://img.shields.io/badge/License-BSD_3--Clause-8A2BE2.svg?style=for-the-badge)](https://opensource.org/licenses/BSD-3-Clause)

![Status](https://img.shields.io/badge/Status-Halted_Development-8A2BE2?style=for-the-badge&logo=vercel)



---

## 🎯 Project Overview  

**Sign Language to Speech Conversion** is a real-time **American Sign Language (ASL) recognition system** powered by **computer vision** and **deep learning**. It translates ASL hand gestures into **both text and speech output**, enhancing accessibility and communication.  

📖 For installation, architecture, usage, and contribution guidelines, visit the **[Project Wiki](https://github.com/RhythmusByte/Sign-Language-to-Speech/wiki)**.  

---

## ✨ Key Features  

- 🔮 **Real-time** hand detection & gesture tracking  

- 🧠 **CNN-based** classification using TensorFlow/Keras  

- 🔊 Simultaneous **text & speech** output  

- 📢 Designed for **accessibility & inclusivity**  

---

## 📊 System Architecture  

| Level 0 | Level 1 | Level 2 |

|---------|---------|---------|

| ![DFD Level 0](DFD_0.png) | ![DFD Level 1](DFD_1.png) | ![DFD Level 2](DFD_2.png) |

For details on **Data Flow Diagrams (DFD), Use Case Diagrams, and System Design**, check the **[Architecture Section](https://github.com/RhythmusByte/Sign-Language-to-Speech/wiki/System-Architecture-&-Design)** in the Wiki.  

---

## 🛠 Tech Stack  

### **Core Technologies**  

![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=python&logoColor=white)  

![OpenCV](https://img.shields.io/badge/OpenCV-5C3EE8?style=for-the-badge&logo=opencv&logoColor=white)  

![TensorFlow](https://img.shields.io/badge/TensorFlow-9D00FF?style=for-the-badge&logo=tensorflow&logoColor=white)  

### **Supporting Libraries**  

![NumPy](https://img.shields.io/badge/NumPy-013243?style=for-the-badge&logo=numpy&logoColor=white)  

![cvzone](https://img.shields.io/badge/cvzone-Community-9D00FF?style=for-the-badge)  

![pyttsx3](https://img.shields.io/badge/pyttsx3-TTS_Engine-8B0000?style=for-the-badge)  

---

## 📂 Repository Structure  

```text

Sign-Language-to-Speech/

├── data/            

├── Application.py   

├── trainedModel.h5  

├── requirements.txt 

└── white.jpg        

```

For a **detailed breakdown of modules and system design**, refer to the **[Project Documentation](https://github.com/RhythmusByte/Sign-Language-to-Speech/wiki)**.  

---

## 📢 Contributing  

We welcome contributions! Before submitting a pull request, please check out the **[Contributing Guide](https://github.com/RhythmusByte/Sign-Language-to-Speech/wiki/Contributions)**.  

---

## 📜 License  

This project is licensed under the **BSD 3-Clause License**. See the full details in the [LICENSE](LICENSE) file.  

---

📌 **For all documentation, including installation, setup, and FAQs, visit the** 👉 **[Project Wiki](https://github.com/RhythmusByte/Sign-Language-to-Speech/wiki)**.