From ba4c963176a17c674960cc9c2311b40d7450f0cd Mon Sep 17 00:00:00 2001 From: Giovanni Campagna Date: Fri, 1 Nov 2019 17:38:38 -0700 Subject: [PATCH] fasttext: use common-crawl not wiki vectors They are trained on a larger corpus and thus better --- decanlp/text/torchtext/vocab.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/decanlp/text/torchtext/vocab.py b/decanlp/text/torchtext/vocab.py index 3bf10df2..3b5a5f73 100644 --- a/decanlp/text/torchtext/vocab.py +++ b/decanlp/text/torchtext/vocab.py @@ -467,7 +467,7 @@ class GloVe(Vectors): class FastText(Vectors): - url_base = 'https://dl.fbaipublicfiles.com/fasttext/vectors-wiki/wiki.{}.vec' + url_base = 'https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.{}.vec' def __init__(self, language="en", **kwargs): url = self.url_base.format(language)