Hardsub2SRT
Get subtitles from a hardsubbed video using OCR
Install / Use
/learn @iWumboUWumbo2/Hardsub2SRTREADME
Hardsub2SRT
Tested on Linux with WSL2
Requirements are opencv for C++ (Install it with your package manager).
Compile threshold.cc with the following command
g++ -O3 -std=c++11 threshold.cc `pkg-config --cflags --libs opencv4` -o threshold
Python requirements are easyocr, jellyfish, srt
To install python requirements navigate to code directory and run this command: pip install -r requirements.txt
If you encounter problems with installing PyTorch (a dependency of easyocr) please visit the website here https://pytorch.org/get-started/locally/ and follow the given instructions to install PyTorch, and then run the command above once again.
Also ffmpeg must be installed
I'll probably convert the bash script to python and also may convert threshold to python but I'm worried about the performance hit. Had to use easyOCR instead of tesseract cause tesseract was just not as accurate.
Here's the link to the tesseract code if you can fix it. https://pastebin.com/7ja1NQeP. I assume it would be more performant.
Related Skills
qqbot-channel
352.0kQQ 频道管理技能。查询频道列表、子频道、成员、发帖、公告、日程等操作。使用 qqbot_channel_api 工具代理 QQ 开放平台 HTTP 接口,自动处理 Token 鉴权。当用户需要查看频道、管理子频道、查询成员、发布帖子/公告/日程时使用。
docs-writer
100.6k`docs-writer` skill instructions As an expert technical writer and editor for the Gemini CLI project, you produce accurate, clear, and consistent documentation. When asked to write, edit, or revie
model-usage
352.0kUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Design
Campus Second-Hand Trading Platform \- General Design Document (v5.0 \- React Architecture \- Complete Final Version)1\. System Overall Design 1.1. Project Overview This project aims t
