Highlights
Stars
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
Comflowyspace is an intuitive, user-friendly, open-source AI tool for generating images and videos, democratizing access to AI technology.
Atomic secret provisioning for NixOS based on sops
简体中文终端更纱黑体+Nerd图标字体库。中英文宽度完美2:1,图标长宽经过调整,不会出现对齐问题,尤其适合作为终端字体。
An incremental parsing system for programming tools
Open singing synthesis platform / Open source UTAU successor
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Unofficial PyTorch implementation of Google AI's VoiceFilter system
基于AI的图片/视频硬字幕去除、文本水印去除,无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API,本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…
Faster Whisper transcription with CTranslate2
devmaxxing / videocr-PaddleOCR
Forked from apm1467/videocrExtract hardcoded subtitles from videos using machine learning
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Instant voice cloning by MIT and MyShell.
Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
Single Image to 3D using Cross-Domain Diffusion for 3D Generation
[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution