Hacker News Reader

junhoyeoon Show HN: BetterOCR combines and corrects multiple OCR engines with an LLM

Yup! But I'm still exploring options. (any recommendations would be welcomed!) Here are some candidates I'm considering:

- https://github.com/mindee/doctr

- https://github.com/open-mmlab/mmocr

- https://github.com/PaddlePaddle/PaddleOCR (honestly I don't know Mandarin so I'm a bit stuck)

- https://github.com/clovaai/donut -- While it's primarily an "OCR-free document understanding transformer," I think it's worth experimenting with. Think I can sort this out by letting the LLM reason through it multiple times (although this will impact performance)

- yesterday got a suggestion to consider https://github.com/kakaobrain/pororo -- don't think development is still active but the results are pretty great on Korean text

junhoyeoon Show HN: BetterOCR combines and corrects multiple OCR engines with an LLM

My pleasure

junhoyeoon Show HN: BetterOCR combines and corrects multiple OCR engines with an LLM

Thanks!

junhoyeoon Show HN: BetterOCR combines and corrects multiple OCR engines with an LLM

Super -- I'm thrilled you enjoyed it!

junhoyeoon Show HN: BetterOCR combines and corrects multiple OCR engines with an LLM

Thanks!

PDF -> Markdown looks like a pretty great use case

Just added box detection support -- maybe I'll start from here https://github.com/junhoyeo/BetterOCR#-box-detection

junhoyeoon Show HN: BetterOCR combines and corrects multiple OCR engines with an LLM

Thinking to add LLaMA or other OSS LLM models soon

junhoyeoon The Web Standard Mini App Problem (2022)

But is there a meaningful "Super App" company in the US?

junhoyeoon Decentralized Web3 Cross-Chain Payment Protocol

it'll look better with number formatting: $9696865.84 -> $9,696,865.84