Feat: Optimize text cleaning by expanding emoji removal support and refining regex for arrow, Arabic, and Hebrew symbol filtering. (#861)

* feat(demo): Add Colab Demo link and ensure output directory creation

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update README.md

* Feat: Optimize text cleaning by expanding emoji removal support and refining regex for arrow, Arabic, and Hebrew symbol filtering.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

fish_speech/text/clean.py

@@ -9,13 +9,20 @@ REPLACE_SYMBOL_REGEX = re.compile(
     "|".join(re.escape(p) for p in SYMBOLS_MAPPING.keys())
 )
 
-
 EMOJI_REGEX = re.compile(
     "["
-    "\U0001f600-\U0001f64f"  # emoticons
+    "\U0001f1e0-\U0001f1ff"  # flags (iOS)
     "\U0001f300-\U0001f5ff"  # symbols & pictographs
+    "\U0001f600-\U0001f64f"  # emoticons
     "\U0001f680-\U0001f6ff"  # transport & map symbols
-    "\U0001f1e0-\U0001f1ff"  # flags (iOS)
+    "\U0001f700-\U0001f77f"  # alchemical symbols
+    "\U0001f780-\U0001f7ff"  # Geometric Shapes Extended
+    "\U0001f800-\U0001f8ff"  # Supplemental Arrows-C
+    "\U0001f900-\U0001f9ff"  # Supplemental Symbols and Pictographs
+    "\U0001fa00-\U0001fa6f"  # Chess Symbols
+    "\U0001fa70-\U0001faff"  # Symbols and Pictographs Extended-A
+    "\U00002702-\U000027b0"  # Dingbats
+    "\U000024c2-\U0001f251"
     "]+",
     flags=re.UNICODE,
 )
@@ -25,12 +32,16 @@ def clean_text(text):
     # Clean the text
     text = text.strip()
 
-    # Replace all chinese symbols with their english counterparts
+    # Replace all Chinese symbols with their English counterparts
     text = REPLACE_SYMBOL_REGEX.sub(lambda x: SYMBOLS_MAPPING[x.group()], text)
 
     # Remove emojis
     text = EMOJI_REGEX.sub(r"", text)
 
+    text = re.sub(r"[←→↑↓⇄⇅]+", "", text)  # Arrows
+    text = re.sub(r"[\u0600-\u06FF]+", "", text)  # Arabic
+    text = re.sub(r"[\u0590-\u05FF]+", "", text)  # Hebrew
+
     # Remove continuous periods (...) and commas (,,,)
     text = re.sub(r"[,]{2,}", lambda m: m.group()[0], text)