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

re-jigged language support/filters

Browse Source
This commit is contained in:
erew123 authored and GitHub committed 2024-04-25 21:24:44 +01:00
1 parent 4d9b44d9a0
commit fd76f496a0
2 files changed
+5 -5
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

script.py
+2 -2
View File
@@ -700,7 +700,7 @@ 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\u3000-\u303F\u0900-\u097F\$]', '', cleaned_part)
cleaned_part = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F]', '', cleaned_part)
# Remove all newline characters (single or multiple)
cleaned_part = re.sub(r"\n+", " ", cleaned_part)
@@ -727,7 +727,7 @@ def output_modifier(string, state):
# Replace multiple instances of certain punctuation marks with a single instance
cleaned_part = re.sub(r"([!?.])\1+", r"\1", cleaned_part)
# Further clean to remove any other unwanted characters
cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\u3000-\u303F\u0900-\u097F\$]', '', cleaned_part)
cleaned_part = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F]', '', 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.
tts_server.py
+3 -3
View File
@@ -1057,7 +1057,7 @@ 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\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u0900-\u097F\$]', '', cleaned_part)
cleaned_part = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F]', '', cleaned_part)
# Remove all newline characters (single or multiple)
cleaned_part = re.sub(r'\n+', ' ', cleaned_part)
output_file = this_dir / "outputs" / f"{output_file_name}_{uuid.uuid4()}_{int(time.time())}.wav"
@@ -1088,13 +1088,13 @@ async def tts_generate(
cleaned_string = html.unescape(standard_filtering(text_input))
cleaned_string = re.sub(r'([!?.])\1+', r'\1', text_input)
# Further clean to remove any other unwanted characters
cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u0900-\u097F\$]', '', cleaned_string)
cleaned_string = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F]', '', 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\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u0900-\u097F\$]', '', cleaned_string)
cleaned_string = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F]', '', cleaned_string)
# Remove all newline characters (single or multiple)
cleaned_string = re.sub(r'\n+', ' ', cleaned_string)
else: