https://github.com/yassin522/fluent-flow

FluentFlow is an AI-powered web application designed to help users improve their public speaking skills. By analyzing body language, voice modulation, and speech content, FluentFlow provides detailed feedback to enhance communication effectiveness.
https://github.com/yassin522/fluent-flow

django flutter opencv python pytorch

Last synced: 3 months ago
JSON representation

FluentFlow is an AI-powered web application designed to help users improve their public speaking skills. By analyzing body language, voice modulation, and speech content, FluentFlow provides detailed feedback to enhance communication effectiveness.

• Host: GitHub
• URL: https://github.com/yassin522/fluent-flow
• Owner: Yassin522
• Created: 2025-03-26T08:14:28.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-03-27T22:46:41.000Z (about 1 year ago)
• Last Synced: 2026-01-03T15:30:41.913Z (6 months ago)
• Topics: django, flutter, opencv, python, pytorch
• Language: Jupyter Notebook
• Homepage:
• Size: 44.3 MB
• Stars: 4
• Watchers: 1
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# FluentFlow

![FluentFlow](https://github.com/user-attachments/assets/60391808-2b11-474b-a40b-1ff968e2d511)

## Overview

FluentFlow is a web application designed to assist users in enhancing their public speaking skills by evaluating their performance across various criteria such as body language, voice modulation, and speech content.

## Features

- **Performance Evaluation:**

  - **Body Movement and Language:** Analyzes gestures, posture, head gaze, and eye gaze to provide insights into non-verbal communication.

  - **Voice Analysis:** Measures aspects such as speed, vocal variation, pauses, and filler words to improve speech delivery.

  - **Script and Language Evaluation:** Examines the script's content, language variation, and overall coherence.

## Technologies Used

### Processing Libraries:

- **Text Processing:** Utilized libraries such as NLTK, SpaCy, and XGBoost for linguistic analysis of the script.

- **Video Processing:** Implemented MoviePy, PyTorch, SciPy, Gensim, and OpenCV to analyze body movements and gestures from video inputs.

- **Audio Processing:** Used Librosa for in-depth vocal feature analysis.

### Development Stack:

- **Frontend:** Built the user interface using Flutter.

- **Backend:** Developed the server-side logic with Django.

---

Developed by **[Alya Almsouti - Hamza Almahrous - Osama Bazo - Yassin Abdulmahdi]** in collaboration with **Damascus University**.

---

## Demo

https://github.com/user-attachments/assets/9c16801a-1907-4990-9fc2-df3a31613951