How galih1250/aslvis26 works
ASLVis26 is a Flask web application for real-time ASL alphabet translation, static-image prediction, and interactive sign-language education. Its user workflow runs through the web interface to Flask endpoints, which invoke YOLO pose detection for camera or uploaded images, or the local Gemma model for chat. The sampled backend excerpt confirms model calls and result generation; the README documents the product capabilities and frontend. The template’s detailed interactions and several route definitions were not sampled, so those links are documented or marked unverified.
Main entry points: app.py Flask Backend · index.html Web Interface
Components 10
Web Interface
- Web Interface
flask-hand/templates/index.html - Flask Backend
flask-hand/app.py
ASL Vision
- Webcam Capture
flask-hand/app.py - Live Translation
flask-hand/app.py - Image Upload
flask-hand/app.py - YOLO Pose Detection
flask-hand/app.py - Annotated Predictions
flask-hand/app.py
AI Education
- Chat Endpoint
flask-hand/app.py - Gemma Assistant
flask-hand/app.py
Other components
- User
Connections 9
- User → Web Interface: uses
README.md - Web Interface → Flask Backend: requests
- Flask Backend → Web Interface: renders
- Webcam Capture → Live Translation: supplies frames
flask-hand/app.py - Live Translation → YOLO Pose Detection: predicts
flask-hand/app.py - Image Upload → YOLO Pose Detection: predicts
flask-hand/app.py - YOLO Pose Detection → Annotated Predictions: annotates
flask-hand/app.py - Flask Backend → Chat Endpoint: routes chat
README.md - Chat Endpoint → Gemma Assistant: generates reply
flask-hand/app.py