Merge branch 'dev' of https://github.com/mozilla/TTS into dev

utils/text/__init__.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 
 import re
+from packaging import version
 import phonemizer
 from phonemizer.phonemize import phonemize
 from TTS.utils.text import cleaners
@@ -28,7 +29,7 @@ def text2phone(text, language):
     seperator = phonemizer.separator.Separator(' |', '', '|')
     #try:
     punctuations = re.findall(PHONEME_PUNCTUATION_PATTERN, text)
-    if float(phonemizer.__version__) < 2.1:
+    if version.parse(phonemizer.__version__) < version.parse('2.1'):
         ph = phonemize(text, separator=seperator, strip=False, njobs=1, backend='espeak', language=language)
         ph = ph[:-1].strip() # skip the last empty character
         # phonemizer does not tackle punctuations. Here we do.
@@ -42,7 +43,7 @@ def text2phone(text, language):
             else:
                 for punct in punctuations:
                     ph = ph.replace('| |\n', '|'+punct+'| |', 1)
-    elif float(phonemizer.__version__) > 2.1:
+    elif version.parse(phonemizer.__version__) >= version.parse('2.1'):
         ph = phonemize(text, separator=seperator, strip=False, njobs=1, backend='espeak', language=language, preserve_punctuation=True)
         # this is a simple fix for phonemizer.
         # https://github.com/bootphon/phonemizer/issues/32

utils/text/cleaners.py

@@ -63,6 +63,19 @@ def convert_to_ascii(text):
     return unidecode(text)
 
 
+def remove_aux_symbols(text):
+    text = re.sub(r'[\<\>\(\)\[\]\"]+', '', text)
+    return text
+
+
+def replace_symbols(text):
+    text = text.replace(';', ',')
+    text = text.replace('-', ' ')
+    text = text.replace(':', ' ')
+    text = text.replace('&', 'and')
+    return text
+
+
 def basic_cleaners(text):
     '''Basic pipeline that lowercases and collapses whitespace without transliteration.'''
     text = lowercase(text)
@@ -84,6 +97,8 @@ def english_cleaners(text):
     text = lowercase(text)
     text = expand_numbers(text)
     text = expand_abbreviations(text)
+    text = replace_symbols(text)
+    text = remove_aux_symbols(text)
     text = collapse_whitespace(text)
     return text
 
@@ -93,5 +108,7 @@ def phoneme_cleaners(text):
     text = convert_to_ascii(text)
     text = expand_numbers(text)
     text = expand_abbreviations(text)
+    text = replace_symbols(text)
+    text = remove_aux_symbols(text)
     text = collapse_whitespace(text)
     return text