Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust

Example UI implementing the RTVI web client

A modular graph-based Retrieval-Augmented Generation (RAG) system

Low-level tests with the ESP32-S2

Implementation for MatMul-free LM.

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

Wunjo CE: Face Swap, Lip Sync, Control Remove Objects & Text & Background, Restyling, Audio Separator, Clone Voice, Video Generation. Open Source, Local & Free.

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Enforce the output format (JSON Schema, Regex etc) of a language model

Implementation of the Wave-U-Net for audio source separation

Code for the paper Hybrid Spectrogram and Waveform Source Separation

High-performance In-browser LLM Inference Engine

This is the admin template for T3 Stack and shadcn ui

The videoDB media collection software

Mold: A Modern Linker 🦠

Total toolhead ecosystem with a focus on modularity, flexibility, and atrocity.

LLRT (Low Latency Runtime) is an experimental, lightweight JavaScript runtime designed to address the growing demand for fast and efficient Serverless applications.

Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch

Real-time object detection on Android using the YOLO network with TensorFlow

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

Read gauges with machine vision and relay the data via Bluetooth Low Energy. We believe in an open Internet of Things.

Reading fuel meters without training a ML/DL model

UFPR-ADMR-v1: a dataset for image-based automatic meter reading containing 2,000 dial meter images obtained on-site by employees of the Energy Company of Paraná (Copel), which serves more than 4 mi…

Python computer vision samples

A fast directory-first photo gallery website, with rich UI, optimized for running on low resource servers (especially on raspberry pi)