search

SamEdwardes / spacypdfreader

Easy PDF to text to spaCy text extraction in Python.
https://samedwardes.github.io/spacypdfreader/
MIT License
33 stars 1 forks source link

Support image(s) to spacy #10

Open SamEdwardes opened 2 years ago

SamEdwardes commented 2 years ago

Support the ability to convert image(s) into a spaCy Doc object. For example:

import spacy
from spacypdfreader import image_reader

nlp = spacy.load("en_core_web_sm")
doc = image_reader(["tests/data/test_img_01.jpg"], nlp)