Robust Speech Recognition via Large-Scale Weak Supervision

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

real time face swap and one-click video deepfake with only a single image

Universal LLM Deployment Engine with ML Compilation

Open standard for machine learning interoperability

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

A tool used to obfuscate python scripts, bind obfuscated scripts to fixed machine or expire obfuscated scripts.

System for AI Education Resource.

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

POT : Python Optimal Transport

PyTorch Neural Network eXchange

A parser, editor and profiler tool for ONNX models.

Powerful handwritten text recognition. A simple-to-use, unofficial implementation of the paper "TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models".

Python scripts performing stereo depth estimation using the CREStereo model in ONNX.