LLM training in simple, raw C/CUDA

Visualizer for neural network, deep learning and machine learning models

Chinese version of GPT2 training code, using BERT tokenizer.

Training YOLOv5/YOLOv9 to detect fire in a video

🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gan…

🔊 Text-Prompted Generative Audio Model

A minimal version of GPT-2 in 175 lines of PyTorch code.

Perceptual Quality Estimator for speech and audio

Tools to Design or Visualize Architecture of Neural Network

Instant voice cloning by MyShell.

高性能开源RTSP流媒体服务器，基于go语言研发，维护和优化：RTSP推模式转发、RTSP拉模式转发、录像、检索、回放、关键帧缓存、秒开画面、RESTful接口、WEB后台管理、分布式负载均衡，基于EasyDarwin构建出了一套基础的流媒体云视频平台架构！

WebRTC/RTSP/RTMP/HTTP/HLS/HTTP-FLV/WebSocket-FLV/HTTP-TS/HTTP-fMP4/WebSocket-TS/WebSocket-fMP4/GB28181/SRT server and client framework based on C++11

AI-Talk allows you to talk with OpenAI GPT.

Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project

《Hello 算法》：动画图解、一键运行的数据结构与算法教程，支持 Java, C++, Python, Go, JS, TS, C#, Swift, Rust, Dart, Zig 等语言。

Official Code for DragGAN (SIGGRAPH 2023)

Cross-platform, customizable ML solutions for live and streaming media.

Skia is a complete 2D graphic library for drawing Text, Geometries, and Images.

An extensible media player for Android

An experimental open-source attempt to make GPT-4 fully autonomous.

A powerful and modular stable diffusion GUI with a graph/nodes interface.

SoftVC VITS Singing Voice Conversion