import spacy_universal_sentence_encoder
# load one of the models: ['en_use_md', 'en_use_lg', 'xx_use_md', 'xx_use_lg']
nlp = spacy_universal_sentence_encoder.load_model('en_use_md')
But at that load_model line, the code tries to go out to the internet. I see in the stack trace lin 261 in language.py which is
self.model = hub.load(self.model_url)
Is there a way to prevent this loading from a url and just load the model locally?
I do
pip install spacy-universal-sentence-encoder
then in code:
But at that load_model line, the code tries to go out to the internet. I see in the stack trace lin 261 in language.py which is
self.model = hub.load(self.model_url)
Is there a way to prevent this loading from a url and just load the model locally?