From 467737b20cdb3cea90c8750d261a3ae084af071a Mon Sep 17 00:00:00 2001 From: Neil Smith Date: Fri, 21 Oct 2016 13:33:30 +0100 Subject: [PATCH] Added more special characters for unaccent --- language_models.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/language_models.py b/language_models.py index bf00875..644338e 100644 --- a/language_models.py +++ b/language_models.py @@ -11,7 +11,7 @@ import itertools from math import log10 import os -unaccent_specials = ''.maketrans({"’": "'"}) +unaccent_specials = ''.maketrans({"’": "'", '“': '"', '”': '"'}) def letters(text): """Remove all non-alphabetic characters from a text -- 2.34.1