{{ word.text }}{{ word.tag }}{{ arc.label }}

Using and customising the models

spaCy comes with free pre-trained models for lots of languages, but there are many more that the default models don't cover. Even if we do provide a model that does what you need, it's almost always useful to update the models with some annotated examples for your specific problem. Our annotation tool Prodigy can help you efficiently label data to train, improve and evaluate your models.

Download modelsTry Prodigy

displaCy Dependency Visualizer

spaCy also comes with a built-in dependency visualizer that lets you check your model's predictions in your browser. You can pass in one or more Doc objects and start a web server, export HTML files or view the visualization directly from a Jupyter Notebook.

import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp(u"displaCy uses JavaScript, SVG and CSS.")
spacy.displacy.serve(doc, style='dep')

Read more