Local LLM runners, AI code assistants, inference engines, and RAG pipelines.
Pure JavaScript OCR for 60 Languages
“> Drop an English image on this page to OCR it! This looks great, and I'd really love to but > Uncaught ReferenceError: progress is not defined EDIT: works now!”
Extract text from images, videos or PDF
Speech recognition in JavaScript
using machine learning and computer vision
Automatic Speech Recognition in TensorFlow
Designed to be recognized by humans and OCR
Build circuit boards faster with computer vision
Text-to-speech and speech-to-text open-source software stack
Set of trained deep learning models for computer vision
Text-to-speech API
OpenCV based multi-object-tracker with various object detection models
I wrote a free Mac app to OCR any text on screen
Text-to-Speech in JavaScript
enhancing physical chessboards with computer vision
I made a computer vision addon for Blender
A Python wrapper for the tesseract-ocr API
An On-Premises, Streaming Speech Recognition System
How we built a TTS-powered tool for learning spelling/foreign languages
Bounding-box labeler tool to generate the training data for YOLO v2
Object Detection in an Hour
n open source Stable Diffusion toolkit and WebUI
Port of OpenAI's Whisper model in C/C++
Live coaching app for remote SWE interviews, uses Whisper and GPT-4
dataset of 10M Stable Diffusion generations
Self-host Whisper As a Service with GUI and queueing
Create your own video clips with Stable Diffusion
State-of-the-art German speech recognition in 284 lines of C++
I made a free transcription service powered by Whisper AI
Stock Photos Using Stable Diffusion
Bulk Creation of Transcripts from YouTube Playlists with Whisper