2 years of OCR training: handwriting recognition went from barely readable to near-perfect
VikParuchuri · x · 2026-10-02
Vik Paruchuri (Marker/Surya) has been training OCR models for two years and says progress on handwriting is astonishing — from barely readable to almost perfect transcription, with a demo image attached. He notes many pages still aren't this good and edge cases remain.
More from Models
- JevBench to add evals for LLM routing, RAG retrieval, and moderation use cases — airesearch12 · 2026-10-02
- Google's Argon battle-tested by 200k+ Googlers daily, not benchmaxxed — Zergylord · 2026-10-02
- JEV claims to be the first System One model hosted in the EU — juanviera23 · 2026-10-02
- Gemini knew a user's mom's name unprompted, then gave three conflicting explanations — Exact_Firefighter864 · 2026-10-02
- GPT-6.1 Sol nearly matches Astra at a quarter of the price on RareBench — danielmckinn0n · 2026-10-02
- New results from PostTrainBench v1.2 are in — mariofilhoml · 2026-10-02