#58 · Primary category： Computer Vision
video-subtitle-extractor
A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.
Project last updated：04/09/26
GitHub Stars
9.4K
Forks
948
Contributors
9
License
Apache-2.0
Why we included this project
Videos with burned-in subtitles are stuck that way unless you retype them, and this desktop app extracts those hard-coded captions into editable SRT files using only local OCR. Nothing gets sent to a cloud service, so there are no per-call API fees and your footage stays on your own machine. The GUI walks you through picking a video or several videos, drawing a box around the subtitle region, and choosing a mode: fast and light, a balanced auto setting that picks models based on your hardware, or a slow precise pass when the quicker ones drop frames. It handles batch extraction, supports dozens of languages, and includes a typo-replacement map for fixing recurring OCR mistakes or removing watermark text. For translators, archivists, or anyone repurposing footage with baked-in captions, it covers a gap that online subtitle tools and raw OCR libraries leave open.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)