deepgeek/Matcha-TTS
2
0
Fork 0
mirror of https://github.com/shivammehta25/Matcha-TTS.git synced 2026-02-05 18:29:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fixing espeak not removing brackets in some cases

Browse Source
This commit is contained in:
Shivam Mehta
2024-11-14 06:39:58 +01:00
parent 77804265f8
commit 7275764a48
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
matcha/text/cleaners.py
View File

@@ -36,6 +36,9 @@ global_phonemizer = phonemizer.backend.EspeakBackend(
# Regular expression matching whitespace: # Regular expression matching whitespace:
_whitespace_re = re.compile(r"\s+") _whitespace_re = re.compile(r"\s+")
# Remove brackets
_brackets_re = re.compile(r"[\[\]\(\)\{\}]")
# List of (regular expression, replacement) pairs for abbreviations: # List of (regular expression, replacement) pairs for abbreviations:
_abbreviations = [ _abbreviations = [
(re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1]) (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
@@ -71,6 +74,8 @@ def expand_abbreviations(text):
def lowercase(text): def lowercase(text):
return text.lower() return text.lower()
def remove_brackets(text):
return re.sub(_brackets_re, "", text)
def collapse_whitespace(text): def collapse_whitespace(text):
return re.sub(_whitespace_re, " ", text) return re.sub(_whitespace_re, " ", text)
@@ -101,6 +106,8 @@ def english_cleaners2(text):
text = lowercase(text) text = lowercase(text)
text = expand_abbreviations(text) text = expand_abbreviations(text)
phonemes = global_phonemizer.phonemize([text], strip=True, njobs=1)[0] phonemes = global_phonemizer.phonemize([text], strip=True, njobs=1)[0]
# Added in some cases espeak is not removing brackets
phonemes = remove_brackets(phonemes)
phonemes = collapse_whitespace(phonemes) phonemes = collapse_whitespace(phonemes)
return phonemes return phonemes