Adding a ner from another pretrained model to a blank model including static vectors

Question

I am very new to Spacy so this question might be kinda dumb, but I can't figure out how to add a NER from an existing model to a blank model. I am following this example: https://spacy.io/api/language#add_pipe and this is my code:

# Build main nlp
main_nlp = spacy.blank("es-419")

# Get spanish ner
spanish_nlp = spacy.load("es_core_news_lg")
main_nlp.add_pipe("ner",source=spanish_nlp, name="spanish_ner")

test_text = # Random text
main_nlp(test_text)

I get the following error: RuntimeError: [E896] There was an error using the static vectors. Ensure that the vectors of the vocab are properly initialized, or set 'include_static_vectors' to False.

Any help would be greatly appreciated!!

Andrea Chavez M · Accepted Answer · 2023-05-30 17:17:41Z

1

I figured out how to fix it, although I am not sure if it is correct. I added the line

main_nlp.vocab.vectors = spanish_nlp.vocab.vectors

before adding the pipe and now the error doesn't show up anymore

answered May 30, 2023 at 17:17

Andrea Chavez M

212 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

aab Over a year ago

This should work fine. Another option would be to pass spanish_nlp.vocab into spacy.blank as in spacy.blank("es", vocab=spanish_nlp.vocab) which copies the whole vocab including the vectors.

Collectives™ on Stack Overflow

Adding a ner from another pretrained model to a blank model including static vectors

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related