Re:DeepSeek OCR
by blindriver on Monday October 20, 2025 @03:00PM
(#45647776)
I attempted OCR using all of the open source models available about 3 months ago, including Llama 4. These were pngs of text using a regular font. Most produced garbage except Llama 4, and even then it was only about 90% accurate. Using OpenAI or Gemini produced much better results but the open source models were really bad.
[ Parent
| on HN ]
There are no comments on this comment yet.