Skip to content
Advertisement

How to use LanguageDetector() from spacy_langdetect package?

I’m trying to use the spacy_langdetect package and the only example code I can find is (https://spacy.io/universe/project/spacy-langdetect):

import spacy
from spacy_langdetect import LanguageDetector
nlp = spacy.load("en_core_web_sm")
nlp.add_pipe(LanguageDetector(), name='language_detector', last=True)
text = 'This is an english text.'
doc = nlp(text)
print(doc._.language)

It’s throwing error: nlp.add_pipe now takes the string name of the registered component factory, not a callable component.

So I tried using the below for adding to my nlp pipeline

language_detector = LanguageDetector()
nlp.add_pipe("language_detector")

But this gives error: Can’t find factory for ‘language_detector’ for language English (en). This usually happens when spaCy calls nlp.create_pipe with a custom component name that’s not registered on the current language class. If you’re using a Transformer, make sure to install ‘spacy-transformers’. If you’re using a custom component, make sure you’ve added the decorator @Language.component (for function components) or @Language.factory (for class components). Available factories: attribute_ruler, tok2vec, merge_noun_chunks, merge_entities, merge_subtokens, token_splitter, parser, beam_parser, entity_linker, ner, beam_ner, entity_ruler, lemmatizer, tagger, morphologizer, senter, sentencizer, textcat, textcat_multilabel, en.lemmatizer

I don’t fully understand how to add it since it’s not really a custom component.

Advertisement

Answer

With spaCy v3.0 for components not built-in such as LanguageDetector, you will have to wrap it into a function prior to adding it to the nlp pipe. In your example, you can do the following:

import spacy
from spacy.language import Language
from spacy_langdetect import LanguageDetector

def get_lang_detector(nlp, name):
    return LanguageDetector()

nlp = spacy.load("en_core_web_sm")
Language.factory("language_detector", func=get_lang_detector)
nlp.add_pipe('language_detector', last=True)
text = 'This is an english text.'
doc = nlp(text)
print(doc._.language)

For built-in components (i.e. tagger, parser, ner, etc.), see: https://spacy.io/usage/processing-pipelines

User contributions licensed under: CC BY-SA
7 People found this is helpful
Advertisement