arielshakaramiro/license-plate-ocr-smolvlm

Vision-language model (SmolVLM-Instruct) based OCR for extracting license plate text from images, returned as structured JSON.

语言：Jupyter Notebook · GitHub 星标：4 · Fork：0

话题：computer-vision · huggingface · license-plate-recognition · ocr · smolvlm · text-extraction · transformers · vision-language-model

在 GitHub 上查看原仓库