From 79a929c92fe8f18c954baa2e3263f7e6a027f7e9 Mon Sep 17 00:00:00 2001
From: ava <hj9990.lee@samsung.com>
Date: Fri, 17 Jan 2020 23:08:48 +0900
Subject: [PATCH 1/2] Correction for text with punctuation and dash

---
 text/cleaners.py | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/text/cleaners.py b/text/cleaners.py
index e2e35c1a8..15d015542 100755
--- a/text/cleaners.py
+++ b/text/cleaners.py
@@ -17,8 +17,10 @@
 from .numbers import normalize_numbers
 
 
-# Regular expression matching whitespace:
+# Regular expression matching whitespace punctuation, dash:
 _whitespace_re = re.compile(r'\s+')
+_punctuation_re = re.compile(r'[!@#$%^&*+-?/,.;]')
+_dash_re = re.compile(r'[-]')
 
 # List of (regular expression, replacement) pairs for abbreviations:
 _abbreviations = [(re.compile('\\b%s\\.' % x[0], re.IGNORECASE), x[1]) for x in [
@@ -65,6 +67,14 @@ def convert_to_ascii(text):
   return unidecode(text)
 
 
+def replace_dash(text):
+  return re.sub(_dash_re, '', text)
+
+
+def collapse_punctuation(text):
+  return re.sub(_punctuation_re, '', text)
+
+
 def basic_cleaners(text):
   '''Basic pipeline that lowercases and collapses whitespace without transliteration.'''
   text = lowercase(text)
@@ -87,4 +97,6 @@ def english_cleaners(text):
   text = expand_numbers(text)
   text = expand_abbreviations(text)
   text = collapse_whitespace(text)
+  text = collapse_punctuation(text)
+  text = replace_dash(text)
   return text

From ddf84929f6e2efc631d8d5c9f44abb6a11a6e143 Mon Sep 17 00:00:00 2001
From: ava <hj9990.lee@samsung.com>
Date: Fri, 17 Jan 2020 23:24:46 +0900
Subject: [PATCH 2/2] Correction for text with punctuation and dash

---
 text/cleaners.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/text/cleaners.py b/text/cleaners.py
index 15d015542..7d85f9daf 100755
--- a/text/cleaners.py
+++ b/text/cleaners.py
@@ -19,7 +19,7 @@
 
 # Regular expression matching whitespace punctuation, dash:
 _whitespace_re = re.compile(r'\s+')
-_punctuation_re = re.compile(r'[!@#$%^&*+-?/,.;]')
+_punctuation_re = re.compile(r'[()!@#$%^&*+?/,.;\"\'\[\]]')
 _dash_re = re.compile(r'[-]')
 
 # List of (regular expression, replacement) pairs for abbreviations: