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

Additional updates re chinese

Browse Source 
CJK Symbols and Punctuation range u3000 > u303F
This commit is contained in:
erew123 authored and GitHub committed 2024-02-21 20:58:57 +00:00
1 parent 7f261bb5e9
commit 015b9033ec
1 file changed
+2 -2
Download Patch File Download Diff File Expand all files Collapse all files
script.py
+2 -2
View File
@@ -663,7 +663,7 @@ def output_modifier(string, state):
# 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\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\$]', '', cleaned_part)
cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\u3000-\u303F\$]', '', cleaned_part)
# Remove all newline characters (single or multiple)
cleaned_part = re.sub(r"\n+", " ", cleaned_part)
@@ -690,7 +690,7 @@ def output_modifier(string, state):
# Replace multiple instances of certain punctuation marks with a single instance
cleaned_part = re.sub(r"([!?.])\1+", r"\1", cleaned_part)
# Further clean to remove any other unwanted characters
cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\$]', '', cleaned_part)
cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\u3000-\u303F\$]', '', cleaned_part)
# Remove all newline characters (single or multiple)
cleaned_part = re.sub(r"\n+", " ", cleaned_part)
# Process the part and give it a non-character name if being used vai API or standalone.