Japan's crowdsourced Minna de Honkoku OCR upgrades to v19 with better kanbun recognition
tkasasagi · x · 2026-09-16
Japan's crowdsourced AI-OCR project Minna de Honkoku has swapped in its v19 recognition model, improving accuracy on okurigana in kanbun (classical Chinese) texts. The project trains on citizen-contributed transcriptions to read kuzushiji, the cursive script found in historical Japanese documents.
More from Models
- TabPFN-3.5 ships, instantly ranking #1 on the classic Kaggle Otto competition — ph_singer · 2026-09-16
- Jev launches: a decision-optimized model claiming 20-200x speed and 40-400x cost gains — FrankFelixAI · 2026-09-16
- HF researcher publicly questions Claude limits: monthly exhausted but weekly 84% left — NielsRogge · 2026-09-16
- Ex-Huawei researcher: AI is great at small-step optimization, but taste and system design remain out of reach — yangyi · 2026-09-16
- First Jev Test Shows Only 80% Agreement with Verified Gemini 3.5 Flash Workflow — mayfer · 2026-09-16
- New model Jev plays Super Mario Bros in real time on fast inference — hardimanjames · 2026-09-16