maminge's repositories
CodeFormer
AI老照片、视频修复工具
danswer
本地化知识库,检索自己文档,网页链接。
InternVL
接近GPT-4V表现的可商用开源模型
EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
kaf-cli-eBookConvert
把txt文本转成epub和mobi电子书的命令行工具(原TmdTextEpub)
EasySpider
A visual no-code/code-free web crawler/spider易采集:一个可视化浏览器自动化测试/数据采集/爬虫软件,可以无代码图形化的设计和执行爬虫任务。别名:ServiceWrapper面向Web应用的智能化服务封装系统。
MuseV
基于视觉条件并行去噪的无限长度和高保真虚拟人视频生成
IDM-VTON
一键换装 IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild
roop
AI人脸替换工具 one-click face swap
MiniCPM-Mobile-LLaMA
MiniCPM-2B: An end-side LLM outperforms Llama2-13B.
mdout
一个Go语言实现的Markdown转PDF命令行工具,基于headless chrome,简单、可靠、易安装、可定制化、易拓展
CnOCR
CnOCR: Awesome Chinese/English OCR Python toolkits based on PyTorch. It comes with 20+ well-trained models for different application scenarios and can be used directly after installation. 【基于 PyTorch/MXNet 的中文/英文 OCR Python 包。】
Bert-VITS2
vits2 backbone with multilingual-bert
localGPT
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
Llama2-Chinese
Llama中文社区,最好的中文Llama大模型,完全开源可商用
free-programming-books-zh_CN
:books: 免费的计算机编程类中文书籍,欢迎投稿
AI-VITS-Howto
AI VITS Howto documents
excalidraw
Virtual whiteboard for sketching hand-drawn like diagrams
AudioSlicerBat
Audio Slicer that uses silence detection to split .wav audio files into several .wav samples.
VITS-fast-fine-tuning
This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion
ctxSip
ctxSip is a Javascript based SIP client that uses WebRTC and WebSockets to connect to your SIP server. The UI is designed to be launched as a popup from within your application. Works well with Kazoo from 2600hz
Umi-OCR
OCR图片转文字识别软件,完全离线。截屏/批量导入图片,支持多国语言、合并段落、竖排文字。可排除水印区域,提取干净的文本。基于 PaddleOCR 。
chatdocs
Chat with your documents offline using AI.
DeepFaceLive
Real-time face swap for PC streaming or video calls
pdf2htmlEX
Convert PDF to HTML without losing text or format.
pdfminer
Python PDF Parser (Not actively maintained). Check out pdfminer.six.
sketch-code
Keras model to generate HTML code from hand-drawn website mockups. Implements an image captioning architecture to drawn source images.