spacy-universal-sentence-encoder

spacy-universal-sentence-encoder copied to clipboard

SpaCy versions required for en_use_lg-0.4.3

2

I have a project that requires `spacy==3.2.1`, and I want to include `en_use_lg-0.4.3` in the project as well. The spaCy requirements specified for the large model are `"spacy_version":">=3.0.3,=3.0.3,

michkessler

TFLite support?

1

We're playing around with running this on the edge and we'd appreciate a version with fewer dependencies - perhaps a version which only depends on tflite. * Has anyone had...

willstott101

Question on certain use case: Checklist Deduplication

1

Given a list of sentences and words, and assuming that I want to deduplicate them, what is the best way to automate the elimination of duplicate items (similar wordings of...

BradKML

It is a amazing work! Appreciate your hard work. I'm met the downloaded model problem, but with the help of https://github.com/MartinoMensio/spacy-universal-sentence-encoder/issues/9#issue-685821614， It work. thanks however, I met another problem, I...

chenhaoenen

Accessing Document vectors and computing similarity is too slow without batching

1

Hi, I use this library and other Spacy models to create Doc objects. I use the pipe() method to apply this to a large corpus of text. The main challenge...

ATAboukhadra

Hi, Thanks for developing spacy USE. Rather than download a model, can we also save/load a model from a local folder? or there is a workaround. I need to use...

lukemao

Request for including a new USE model

2

Hi, thanks for providing these USE-Spacy interfaces!! Recently Google released another USE, now as a conditional masked language model, please find it here https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base/1. My question is if that's possible...

adaj

cant change vocab vector

2

When I try to change the word embeddings nothing happens ` import spacy_universal_sentence_encoder nlp_use = spacy_universal_sentence_encoder.load_model('en_use_lg') vector = nlp_use('her').vector nlp_use.vocab.set_vector("Ertha", vector) print(vector) print(nlp_use("Ertha")) ` The two print statements should be...

DanielBeck93

How to use this with a downloaded model?

11

Hello, I am trying to use this inside of a Docker image. I have downloaded the model separately from [here](https://tfhub.dev/google/universal-sentence-encoder-large/5), and I have performed the `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.3.1/en_use_lg-0.3.1.tar.gz#en_use_lg-0.3.1` as a...

jrruethe

Problems installing models on SpaCy 2.3.2

2

I installed the models as per the directions in the README but they are not showing up in Spacy: ```$ python -m spacy validate ✔ Loaded compatibility table ====================== Installed...

ckmaresca