Trending Projects

A curated list of open-source projects and applications integrated with Hugging Face's machine learning libraries.

TensorFlowASR is an almost state-of-the-art automatic speech recognition library in TensorFlow 2 for vibe coders.

A Python library for generating photorealistic training images using the Blender 3D software.

A Python-based webservice API that provides an easy-to-use interface for the OpenAI Whisper automatic speech recognition model.

A portable accelerated SQL query, search, and LLM-inference engine for data-grounded AI apps and agents.

Integrate ChatGPT into your own Discord bot with this Python library.

An AI-powered bot that automates live streaming video clipping, processing, and publishing across popular platforms.

A C++ library for restoring defocused and blurred photos/images.

A Python library for deep reinforcement learning in finance, with dynamic datasets and market environments.

A pre-trained Chinese XLNet model for natural language processing tasks.

Unofficial Parallel WaveGAN repository with PyTorch implementation of various neural vocoders for speech synthesis.

Ultrafast serverless GPU inference, sandboxes, and background jobs for AI-focused developers.

A Python implementation of the neural algorithm for artistic style transfer.

A Python library that provides a framework for building intelligent, agentic workflows and AI agents.

Truncated diffusion model for real-time end-to-end autonomous driving, using AI tools.

A PyTorch implementation of the Capsule Graph Neural Network (CapsGNN) for graph classification tasks.

A Python library that provides dynamic thresholding (CFG scale fix) for Stable Diffusion AI models.

A library for generating captions for images using deep learning models.

An AI-powered crypto trading bot that automates futures trading on platforms like Binance and Bitget.

A multi-agent framework for end-to-end film automation in virtual 3D spaces, focused on AI-powered filmmaking.

Portable package for running Hunyuan3D, an AI-powered 3D generation and editing tool, on Windows

A C++ implementation of popular object detection frameworks like Cascade R-CNN.

A pure PyTorch implementation of the NVIDIA paper on Instant Training of Neural Graphics Primitives.

Official implementation of the RecurrentGPT paper for interactive generation of long text using AI.

A comprehensive tutorial for the LangChain library, a framework for building applications with large language models.

A robust and versatile monocular visual-inertial state estimator for robotics and computer vision applications.

A visual-inertial calibration toolbox for cameras and IMUs, enabling precise sensor fusion.

An all-in-one AI automation platform for security, IT, and infrastructure teams, with workflows, agents, and more.

A C++ library for audio and music analysis, description, and synthesis, with Python bindings.

A book on the foundations and models of machine translation, including deep learning and neural machine translation.

Optical character recognition for Japanese manga comics, built with Python and deep learning.

A strong baseline and bag of tricks for deep person re-identification in computer vision.

Keras Temporal Convolutional Network (TCN) library for building deep learning models with temporal dependencies.

A Swift library that allows developers to query Apple Health data using natural language

A curated list of papers about using deep learning for protein design.

Collection of CVPR and NeurIPS poster examples and templates for AI/ML researchers and developers.

Real-time motion retargeting system that maps human movements to diverse humanoid robots on CPU.

An open-source library for building generative multimodal AI models, with a focus on foundation models, in-context learning, and multimodal pretraining.

A PyTorch implementation of the PWC-Net, a CNN-based optical flow estimation model for computer vision tasks.

A Java toolkit for text similarity calculation and sentiment analysis, useful for NLP tasks.

An implementation for detailed localized image and video captioning using large multimodal models.

A collection of codes for Reconfigurable Intelligent Surface (RIS) research related to 6G and wireless communication.

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing

Hibiki is a Rust library for building real-time speech translation models for AI-powered applications.

This course teaches beginners about Edge AI, including concepts, models, inference, optimization, and developing intelligent Edge AI agents.

A curated list of accepted papers from various AI, ML, and robotics conferences.

Minimal and annotated implementations of key ideas from modern deep learning research.

Variational autoencoder implementation in TensorFlow and PyTorch, including inverse autoregressive flow.

A curated collection of machine learning and deep learning resources for developers.

A curated list of 99 machine learning projects for anyone interested in learning and building with ML