Created
January 10, 2018 23:48
-
-
Save anonymous/4b0ee04cef7f703beb2f539d5577299f to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# coding: utf8 | |
"""Load vectors for a language trained using fastText | |
https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md | |
Compatible with: spaCy v2.0.0+ | |
""" | |
from __future__ import unicode_literals | |
import plac | |
import numpy | |
import spacy | |
from spacy.language import Language | |
lang = "nb" | |
vectors_loc = "wiki.no.vec" | |
if lang is None: | |
nlp = Language() | |
else: | |
# create empty language class – this is required if you're planning to | |
# save the model to disk and load it back later (models always need a | |
# "lang" setting). Use 'xx' for blank multi-language class. | |
nlp = spacy.blank(lang) | |
with open(vectors_loc, 'rb') as file_: | |
header = file_.readline() | |
nr_row, nr_dim = header.split() | |
nlp.vocab.reset_vectors(width=int(nr_dim)) | |
for line in file_: | |
line = line.rstrip().decode('utf8') | |
pieces = line.rsplit(' ', int(nr_dim)) | |
word = pieces[0] | |
vector = numpy.asarray([float(v) for v in pieces[1:]], dtype='f') | |
nlp.vocab.set_vector(word, vector) # add the vectors to the vocab | |
nlp.to_disk('norsk.model') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment