Update utils/text_norm.py

utils/text_norm.py

@@ -6,7 +6,12 @@ from utils.norm_config import norm_config
 
 
 def text_normalize(
-    text, iso_code, lower_case=True, remove_numbers=True, remove_brackets=False
+    text,
+    iso_code="xxx",
+    lower_case=True,
+    remove_numbers=False,
+    remove_brackets=False,
+    rm_extra_spaces=False,
 ):
 
     """Given a text, normalize it by changing to lower case, removing punctuations, removing words that only contain digits and removing extra spaces
@@ -95,7 +100,7 @@ def text_normalize(
 
         normalized_text = unidecode(normalized_text)
 
-    # Remove extra spaces
-    normalized_text = re.sub(r"\s+", " ", normalized_text).strip()
+    if rm_extra_spaces:
+        normalized_text = re.sub(r"\s+", " ", normalized_text).strip()
 
     return normalized_text