mengguiyouziyi's repositories
FunpySpiderSearchEngine
Word2vec 千人千面 个性化搜索 + Scrapy2.3.0(爬取数据) + ElasticSearch7.9.1(存储数据并提供对外Restful API) + Django3.1.1 搜索
Bleualign
Machine-Translation-based sentence alignment tool for parallel text
ChatGLM-Tuning
一种平价的chatgpt实现方案, 基于ChatGLM-6B + LoRA
crawler
爬虫项目: 主要爬取抖音,好看,快手,头条,土豆,网易新闻,qq视频等短视频数据
cube-studio
Cloud native one-stop machine learning platform, Multi-user, Dataleap, Notebook, Drag-and-Drop pipeline, Multi-machine multi-card distributed training, Automl, Inference, Edge computing, Federation schedule, Real-time training, large models, AIHub
DecryptLogin
DecryptLogin: APIs for loginning some websites by using requests.
GFPGAN
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
insuranceqa-corpus-zh
:helicopter: 保险行业语料库,聊天机器人
interviews
Everything you need to know to get the job.
LiveRecorder
you-live - A live recorder focus on China mainland livestream sites(A站/B站/斗鱼/快手)
mediawiki-services-machinetranslation
GitHub mirror of the mediawiki/services/machinetranslation repository. Development happens at https://gerrit.wikimedia.org. Please see https://www.mediawiki.org/wiki/Developer_account if you wish to contribute.
mengguiyouziyi.github.io
my blogs
PaddleOCR
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 deployment among server, mobile, embedded and IoT devices)
python-course
最快的Python入门教程,包含Python基础、爬虫、Django、Flask等内容。
QingTingFM
qingting.fm蜻蜓FM付费内容下载
real-url
获取斗鱼&虎牙&哔哩哔哩&抖音&快手等 58 个直播平台的真实流媒体地址(直播源)和弹幕,直播源可在 PotPlayer、flv.js 等播放器中播放。
social-auto-upload
自动化上传视频到社交媒体:抖音、小红书、视频号、tiktok、youtube、bilibili
TiktokAutomation
2023年4、5月份心血来潮,想做TK,为了实现矩阵运营,开启此项目,但是最后由于各种原因,无法继续。现在将项目公开,希望能对后面做自媒体的有所帮助。本项目包括本地代理IP的配置,outlook邮箱申请(图片验证需要手动处理一下),邮箱验证码自动读取,tk账号注册和登录(这里也存在问题,单次可行,第二次会被识别次数太多,细节看readme),tk的模拟浏览视频,tk视频下载,视频搬运前的剪辑处理等等
video-srt
这是一个可以识别视频语音自动生成字幕SRT文件的开源命令行工具。
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.
YakuYaku
翻译姬:致力于小众领域的机器翻译
zhihu-upload
知乎上传视频