Keep one space between numbers in replace_blank

cosyvoice/utils/frontend_utils.py

@@ -120,13 +120,22 @@ def should_merge(_text: str):
 # remove blank between chinese character
 def replace_blank(text: str):
     out_str = []
-    for i, c in enumerate(text):
-        if c == " ":
-            if ((text[i + 1].isascii() and text[i + 1] != " ") and
-                    (text[i - 1].isascii() and text[i - 1] != " ")):
-                out_str.append(c)
-        else:
-            out_str.append(c)
+    i = 0
+    n = len(text)
+    while i < n:
+        if text[i] != " ":
+            out_str.append(text[i])
+            i += 1
+            continue
+        j = i
+        while j < n and text[j] == " ":
+            j += 1
+        left = text[i - 1] if i else ""
+        right = text[j] if j < n else ""
+        if (left and right and left.isascii() and left != " " and
+                right.isascii() and right != " "):
+            out_str.append(" ")
+        i = j
     return "".join(out_str)
 
 

test_frontend_utils.py

@@ -0,0 +1,24 @@
+import unittest
+
+from cosyvoice.utils.frontend_utils import replace_blank
+
+
+class ReplaceBlankTests(unittest.TestCase):
+    def test_doubled_space_between_numbers_stays_a_space(self):
+        self.assertEqual(replace_blank("版本 12  34"), "版本12 34")
+
+    def test_single_space_between_numbers_stays(self):
+        self.assertEqual(replace_blank("版本 12 34"), "版本12 34")
+
+    def test_space_beside_chinese_is_still_removed(self):
+        self.assertEqual(replace_blank("你 a"), "你a")
+
+    def test_single_space_between_ascii_words_stays(self):
+        self.assertEqual(replace_blank("a b"), "a b")
+
+    def test_doubled_space_between_ascii_words_collapses_to_one(self):
+        self.assertEqual(replace_blank("a  b"), "a b")
+
+
+if __name__ == "__main__":
+    unittest.main()