From d4647573cdff3def80c62d7f1d25ddc4f0d19af1 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Thu, 18 Apr 2024 19:58:31 +0100
Subject: [PATCH] Add files via upload

---
 script.py     | 4 ++--
 tts_server.py | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/script.py b/script.py
index eab0e1d..4dbff04 100644
--- a/script.py
+++ b/script.py
@@ -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\$]', '', 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\u0900-\u097F\$]', '', 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\$]', '', 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\u0900-\u097F\$]', '', 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.
diff --git a/tts_server.py b/tts_server.py
index f77f10e..604acae 100644
--- a/tts_server.py
+++ b/tts_server.py
@@ -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]\$', '', cleaned_part)
+                cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u0900-\u097F\$]', '', 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]\$', '', cleaned_string)
+                cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u0900-\u097F\$]', '', cleaned_part)
                 # 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]\$', '', cleaned_string)
+                cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u0900-\u097F\$]', '', cleaned_part)
                 # Remove all newline characters (single or multiple)
                 cleaned_string = re.sub(r'\n+', ' ', cleaned_string)
             else: