BobbyLi's repositories
WeChatMsg
提取微信聊天记录，将其导出成HTML、Word、CSV文档永久保存，对聊天记录进行分析生成年度聊天报告
docxjs
Docx rendering library
xhtml2pdf
A library for converting HTML into PDFs using ReportLab
html2pdf.js
Client-side HTML-to-PDF rendering using pure JS.
myXLSX
Viewing XLSX in browser with formatting
pdfium-binaries
📰 Binary distribution of PDFium
text2vec
text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。
rembg
Rembg is a tool to remove images background
ChatFiles
Have a conversation with files ｜与你的文件对话
chatgpt-chrome-extension
A ChatGPT Chrome extension. Integrates ChatGPT into every text box on the internet.
bark
🔊 Text-Prompted Generative Audio Model
DB
A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".
pdf2htmlEX
Convert PDF to HTML without losing text or format.
Windows.Media.Ocr.Cli
Using UWP API Windows.Media.Ocr as an executable command line tool
deepdoctection
A Repo For Document AI
NetOffice
🌌 Create add-ins and automation code for Microsoft Office applications.
poi-tl
Generate awesome word(docx) with template
libxlsxwriter
A C library for creating Excel XLSX files.
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
simpread
简悦 ( SimpRead ) - 让你瞬间进入沉浸式阅读的扩展
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 。
free-google-translate
Free Google Translator API 免费的Google翻译
openvino_notebooks
📚 Jupyter notebook tutorials for OpenVINO™
video-subtitle-extractor
视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.
Text-Grab
Use OCR in Windows 10 quickly and easily with Text Grab. With optional background process and popups.
page_dewarp
Text page dewarping using a "cubic sheet" model
SAN
Syntax-Aware Network for Handwritten Mathematical Expression Recognition
Pix2Text
Pix In, Latex & Text Out. Recognize Chinese, English Texts, and Math Formulas from Images.
HummusJS
Node.js module for high performance creation, modification and parsing of PDF files and streams
docscan
Docscan is a document scanner. Take a photo of your documents and frame it.