babybearofficial's starred repositories
Image-to-Text-OCR
Image to Text is a web tool to extract text from any image using OCR
marker-api
Easily deployable 🚀 API to convert PDF to markdown quickly with high accuracy.
stream-rec
Automatic streaming record tool. 虎牙/抖音/斗鱼/Twitch/PandaTV直播，弹幕自动录制
csdn-spider
🍥 CSDN 爬虫，批量爬取指定用户全部博文并输出为 markdown 格式
dual-wechat
如何在Mac上通过脚本实现微信双开，并通过自动操作创建应用程序，修改图标后直接当作第二个微信使用，无需打开终端输入代码，且双开后无终端出现。
bilibili-API-collect
哔哩哔哩-API收集整理【不断更新中....】
statsmodels
Statsmodels: statistical modeling and econometrics in Python
RxInfer.jl
Julia package for automated Bayesian inference on a factor graph with reactive message passing
CapsWriter-Offline
CapsWriter 的离线版，一个好用的 PC 端的语音输入工具
MyIP
The best IP Toolbox. Easy to check what's your IPs, IP geolocation, check for DNS leaks, examine WebRTC connections, speed test, ping test, MTR test, check website availability, whois search and more! || 🇨🇳 可能是最好用的IP工具箱。轻松检查你的 IP，IP 地理位置，检查DNS泄漏，检查 WebRTC 连接，速度测试，ping 测试，MTR测试，检查网站可用性，查询 Whois 信息等等。
epub_to_audiobook
EPUB to audiobook converter, optimized for Audiobookshelf
label-studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
tree-sitter
An incremental parsing system for programming tools
firefly-iii
Firefly III: a personal finances manager
ML-YouTube-Courses
📺 Discover the latest machine learning / AI courses on YouTube.
Chinese-LangChain
中文langchain项目|小必应，Q.Talk，强聊，QiangTalk
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
EasyInstruct
[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.
ChineseNRE
中文实体关系抽取，pytorch，bilstm+attention
sort-google-scholar
Sorting Google Scholar search results based on the number of citations
crawlee
Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.