wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-09 11:16:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

padding idx for embedding layer

Browse Source
This commit is contained in:
erogol
2020-02-20 12:24:54 +01:00
parent e7ef4e9050
commit 957f7dcbc5
3 changed files with 19 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
utils/text/cleaners.py
+17
View File
@@ -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