Error while loading vector from Glove in Spacy

Question

I am facing the following attribute error when loading glove model:

Code used to load model:

nlp = spacy.load('en_core_web_sm')
tokenizer = spacy.load('en_core_web_sm', disable=['tagger','parser', 'ner', 'textcat'])
nlp.vocab.vectors.from_glove('../models/GloVe')

Getting the following atribute error when trying to load the glove model:

AttributeError: 'spacy.vectors.Vectors' object has no attribute 'from_glove'

Have tried to search on StackOverflow and elsewhere but can’t seem to find the solution. Thanks!

From pip list:

spacy version: 3.1.4
spacy-legacy 3.0.8
en-core-web-sm 3.1.0

Asked By: beta

||

Source

Answer 1

spacy version: 3.1.4 does not have the feature from_glove.

I was able to use nlp.vocab.vectors.from_glove() in spacy version: 2.2.4.

If you want, you can change your spacy version by using:

!pip install spacy==2.2.4 on your Jupyter cell.

Answered By: God Is One

Answer 2

Use spacy init vectors to load vectors from word2vec/glove text format into a new pipeline: https://spacy.io/api/cli#init-vectors

Answered By: aab

Error while loading vector from Glove in Spacy

Question:

Answers: