61–65 of 65 posts
Offtopic, but what's the best OCR that can run offline on browsers with js/wasm with reasonable CPU/memory cost? Working on a hobby project that interacts with user handwriting on . Tried some CNN models for digits but had trouble with characters.
Note that I haven't tried any of them, but tesseract is still likely the leading open source OCR that works with CPU.
I've been really impressed with this model specifically because of how insanely cheap it is: https://replicate.com/ibm-granite/granite-vision-3.3-2b I didn't expect IBM to be making relevant AI models but this thing is priced at $1 per 4,000,000 output tokens... I'm using it to transcribe handwritten input text and it works very well and super fast.
What is needed to evaluate OCR for most business applications (above everything else) is accuracy. Some results look plausible but are just plain wrong. That is worse than useless. Example: the "Table" sample document contains chemical substances and their properties. How many numbers did the LLM output and associate correctly? That is all that matters. There is no "preference" aspect that is relevant until the data…