Show HN: CPU-only fast OCR for screenshots, images, PDFs, webpages (github.com) 9 points by mrkn1 1mo ago ↗ HN
[–] explosion-s 1mo ago ↗ Why is no GPU a pull here? Is there usually an activation overhead GPU request or something?
[–] quanglee 1mo ago ↗ Do you have some benchmark on how fast it is on cpu? I checked the repo and the huggingface page but only found gpu-based benchmarks [–] mrkn1 1mo ago ↗ I have not. My experience has been a few seconds for an 1024x1024 with medium density of text, FWIW. Feel free to try it on a few test images, model is pretty small and fast, but yeah no formal evals on CPU.
[–] mrkn1 1mo ago ↗ I have not. My experience has been a few seconds for an 1024x1024 with medium density of text, FWIW. Feel free to try it on a few test images, model is pretty small and fast, but yeah no formal evals on CPU.
5 comments
[ 421 ms ] story [ 670 ms ] thread