Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
ZennyKennyΒ 
posted an update 14 days ago
Post
318
Anyone got the scoop on a good OCR model that's available on inference?

Keen to make use of an endpoint (gated or not -- happy to pay for usage) for a personal project, but not so keen to pay for the GPU hosting myself.

πŸ™ˆπŸ™ˆπŸ™ˆ

BRUTAL.

image

You can use a VLM if you really want an API. That being said, there are a lot of OCR models that can run on CPU (albeit slow)

Β·

Yeah totally get there are options out there, but was just looking for some pointers from people who might have used some of the options and could offer advice on the best one in their opinion.

Decided to go with PaddleOCR: https://github.com/PaddlePaddle/PaddleOCR

Ended up going with Paddle: https://github.com/PaddlePaddle/PaddleOCR

Good performance and totally open-source. Using on a RunPod container works great!