Private voice keyboard, AI chat, images, webcam, recordings, voice control with >= 4 GiB of VRAM.

voice to code on linux with kaldi

🔈 A screenreader for Neovim. Supports infix operator identification for Haskell and Scala, as well as Python 3 specific AST analysis for more intelligible reading. Awarded 1st place at the QUT Code Network Winter Hackathon 2017.

Senior (sensory impaired) adapted HW audio book player with radio and auto-generated daily update (Raspberry Pi Zero)

A simple app/hardware solution to send keystrokes from one computer to another over Bluetooth LE. No software required on recipient machine

Dual Voice for NVDA (adding support for multilingual speech to a famous screen reader namely NVDA).

Final year college project, based on Digital Image Processing, Computer Vision and Deep Learning. It is aimed towards helping visually impaired people to access digital media and information of their surrounding, through text recognition and objection classification.

Cod ar gyfer 'Macsen' - prototeip o gynorthwyydd digidol Cymraeg i'r Raspberry Pi // Code for 'Macsen' - a prototype Welsh language digital assistant for the Raspberry Pi

Local, voice-enabled AI assistant on the terminal

🔮 Sign Language Translator for ASL with a gesture glove built for ECESCON9 contest

Turns switch presses to Morse - and then sends this as Text / Mouse movements to a BLE compatible device

Artificial intelligence programmed in Python to perform searching on Google and YouTube by voice command.

Virtual Assistant project done in the Middlesex University with Dr. Nawaz Khan by scholarship of the ErasmusPlus program.

Entirely Local AI Voice Assistant - Created using LangChain, Ollama, Whisper, Speech Recognition, and Sapi5

Deep learning scripts used to accurately predict human-robot system dynamics for future prosthesis control methods

A Python-based application designed specifically for visually impaired users, enabling them to seamlessly send and receive emails using intuitive speech commands. This innovative solution enhances accessibility and independence by allowing users to manage their email communication effortlessly, utilizing voice recognition technology to ensure a us.

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.

Open Source Sign Language Recognition Platform

Assistive switchbox. Maps multiple switches to keyboard and mouse events. End-user configurable.

Small set of scripts to map data (letters, words, phrases) to a grid template based on frequency distribution.