Beginner, advanced, expert level Rust training material

Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

PyO3-based Rust bindings of the NumPy C-API

ncnn is a high-performance neural network inference framework optimized for the mobile platform

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

A lightweight WebAssembly runtime that is fast, secure, and standards-compliant

WasmEdge is a lightweight, high-performance, and extensible WebAssembly runtime for cloud native, edge, and decentralized applications. It powers serverless apps, embedded functions, microservices,…

Python bindings for CosyVoice3 TTS using Candle. Has the characteristics of small size, fast speed, and does not rely on libraries such as Pytorch.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Cross-platform audio I/O library in pure Rust

HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026

Suno-like music generation studio for HeartMuLa/heartlib - AI-powered music creation with reference audio style transfer

Utilizes ONNX Runtime for TTS model.

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Yet another minimalist deep-learning framework optimized for inference

Rust audio playback library

GPT-SoVITS ONNX Inference Engine & Model Converter

Easily train a good VC model with voice data <= 10 mins!

SoftVC VITS Singing Voice Conversion

A GPT-SoVITS Text-to-Speech (TTS) implementation in Rust, leveraging ONNX Runtime for near real-time performance on CPUs.

Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

Official inference code for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

so-vits-svc fork with realtime support, improved interface and more features.

🎃 A fast, out-of-the-box terminal built for AI coding.

[CVPR2026]🚀🚀🚀Official code for the paper "YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection." *(YOLO = You Only Look Once)* 🔥🔥🔥