kromskii2/alltalk_tts
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Regex improvement

Browse Source 
Add greedy option to avoid apostrophe being removed
Add accentuated character for foreign language
This commit is contained in:
nicobubulle committed 2024-01-03 16:54:25 +01:00
1 parent e9feae12ad
commit 0ec580539a
1 file changed
+3 -3
Download Patch File Download Diff File Expand all files Collapse all files
tts_server.py
+3 -3
View File
@@ -1006,7 +1006,7 @@ async def tts_generate(
# Replace multiple exclamation marks, question marks, or other punctuation with a single instance
cleaned_part = re.sub(r'([!?.])\1+', r'\1', part)
# Further clean to remove any other unwanted characters
cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"]', '', cleaned_part)
cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"À-ÿ]\$', '', cleaned_part)
# Remove all newline characters (single or multiple)
cleaned_part = re.sub(r'\n+', ' ', cleaned_part)
output_file = this_dir / "outputs" / f"{output_file_name}_{uuid.uuid4()}_{int(time.time())}.wav"
@@ -1030,13 +1030,13 @@ async def tts_generate(
cleaned_string = html.unescape(standard_filtering(text_input))
cleaned_string = re.sub(r'([!?.])\1+', r'\1', text_input)
# Further clean to remove any other unwanted characters
cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"]', '', cleaned_string)
cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"À-ÿ]\$', '', cleaned_string)
# Remove all newline characters (single or multiple)
cleaned_string = re.sub(r'\n+', ' ', cleaned_string)
elif text_filtering == "standard":
cleaned_string = re.sub(r'([!?.])\1+', r'\1', text_input)
# Further clean to remove any other unwanted characters
cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"]', '', cleaned_string)
cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"À-ÿ]\$', '', cleaned_string)
# Remove all newline characters (single or multiple)
cleaned_string = re.sub(r'\n+', ' ', cleaned_string)
else: