Show HN: I digitized 66,010 pages from a 32-year student broadcast archive

Category: other

Tags: digital-archive, ocr, privacy, korean, preservation

Score: 5.0/10 (Innovation: 4, Technical: 5, Documentation: 7, Utility: 4)

A digital preservation project that scanned and processed 66,010 pages of student radio broadcast cue sheets from 1988–2019, including redaction, OCR, and pseudonymization. It provides a documented workflow, a small demo, and a review web app, with the full dataset on Hugging Face. The project is notable for its human-centered archival approach and transparent process documentation.

Target audience: archivists, historians, data engineers, privacy engineers

Repository: https://voku-pub.newtypecola.workers.dev/ · Python · NOASSERTION

View on Hacker News