Trending Projects

An interactive C live coding environment for developers building AI-powered applications.

Audio Spectrogram Transformer (AST) for audio classification and representation learning tasks.

Interface for OuteTTS models, a Python library for text-to-speech using transformer-based models.

SimpleRecon is a 3D reconstruction library that uses a novel approach without 3D convolutions, optimized for computer vision tasks.

Automatically generate YouTube subtitles using OpenAI's Whisper speech recognition model

A research framework for easy and efficient training of Generative Adversarial Networks (GANs) based on PyTorch.

A low-latency prediction-serving system written in C++ for AI and ML applications.

This is a Python library for learning the principles of machine learning.

A Python extension for the Stable Diffusion WebUI that enables high-quality lip-sync animation for talking face generation.

Fastest text 'uwuifier' written in Rust, targeting vibe coders who use AI tools.

A PyTorch-based object detection library with a Receptive Field Block Network for fast and accurate performance.

A collection of concise and beautiful algorithms written in the Julia programming language.

A TensorFlow-based implementation of a deep Siamese LSTM network for capturing phrase/sentence similarity using character/word embeddings.

A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.

This is a source code and dataset for an enhanced language representation model ERNIE, focused on using informative entities.

A unified UI and API for processing and training images for facial recognition across various AI tools.

csghub-server is a backend server for managing datasets, models, and running inference/finetuning for AI/ML applications.

A Python library for processing and analyzing scientific audio data, particularly for bird song detection and recognition.

This is a Python-based chatbot built using the LLaMA v2 language model, useful for developers exploring AI-powered conversational applications.

A Python implementation of training for GPT2, supporting TPUs for AI-focused developers.

A labeling extension for Automatic1111's Stable Diffusion web UI, focused on AI-assisted content tagging.

A curation of the latest CVPR (Computer Vision and Pattern Recognition) papers, code, and demos for AI-powered developers.

A library that provides seamless model explainability for transformers models in just 2 lines of code.

A multilingual dialog corpus for building chatbots and conversational AI systems.

A repository with exercises for the Deep Learning textbook, focused on machine learning and AI.

A Python SDK/API for reverse-engineered Google Bard, a powerful AI chatbot.

StableAnimator is an end-to-end video diffusion framework for synthesizing high-quality, ID-preserving videos from a reference image and pose sequence.

A toolbox to generate adversarial examples that fool neural networks in various ML frameworks.

An open-source Chinese AI dungeon game that uses the OpenAI ChatGPT API for storytelling.

Fast, modular reference implementation of Semantic Segmentation algorithms in PyTorch for vibe coders.

Omniglot dataset for one-shot learning experiments in MATLAB

A Go library for lattice-based homomorphic encryption, enabling secure multi-party computation.

This repo maps the ecosystem of AI guidelines, principles, ethics, standards, and regulations.

A TensorFlow-based face recognition neural network library for Python developers.

A depth map library for use with the Control Net extension for the Automatic1111/stable-diffusion-webui.

An efficient C++20 GPU numerical computing library with Python-like syntax for high-performance computing.

A Python library that provides Llama-3 agents capable of browsing the web and interacting with users.

SpeechGPT is a Python library for building speech-based applications using large language models.

A comprehensive implementation of all reinforcement learning algorithms in a simpler way.

A Python re-implementation of the pi0 vision-language-action (VLA) model for developers working with AI tools.

An OpenMMLab toolkit for 3D human parametric model development and benchmarking.

One-stage Retinex-based Transformer for Low-light Image Enhancement

This Python library speeds up Stable Diffusion, a popular AI image generation model.

This repository provides code and models for large-scale computer vision research projects using AI tools.

NeuralSVG is an official Python implementation of a tool for generating SVG images from neural networks.

Python code to fuse multiple RGB-D images into a TSDF voxel volume for 3D reconstruction.

An open-source virtual assistant for Ubuntu-based Linux distributions, focused on speech recognition and natural language processing.

A tool suite for texture and 3D model compression, optimization, and analysis using CPUs, GPUs, and APUs.

Use pre-trained transformer models like BERT, GPT-2, and XLNet in the spaCy NLP library.

Korean BERT pre-trained model for natural language processing tasks in the Korean language.