Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

better version control for phonemizer

This commit is contained in:
erogol 2020-03-02 12:53:55 +01:00
parent a68012aec2
commit c825b63d4c
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
datasets/preprocess.py
View File

@ -84,7 +84,7 @@ def mozilla_de(root_path, meta_file):
for line in ttf: for line in ttf:
cols = line.strip().split('|') cols = line.strip().split('|')
wav_file = cols[0].strip() wav_file = cols[0].strip()
text = cols[1].strip() text = cols[1].strip()
folder_name = f"BATCH_{wav_file.split('_')[0]}_FINAL" folder_name = f"BATCH_{wav_file.split('_')[0]}_FINAL"
wav_file = os.path.join(root_path, folder_name, wav_file) wav_file = os.path.join(root_path, folder_name, wav_file)
items.append([text, wav_file, speaker_name]) items.append([text, wav_file, speaker_name])

5
utils/text/__init__.py
View File

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