fix a bug in Mandarin pypinyin_g2p_phone

chintu619 · Mar 25, 2022 · 50269e8 · 50269e8
1 parent 253eb17
commit 50269e8
Showing 1 changed file with 4 additions and 2 deletions.
diff --git a/espnet2/text/phoneme_tokenizer.py b/espnet2/text/phoneme_tokenizer.py
@@ -199,9 +199,11 @@ def pypinyin_g2p_phone(text) -> List[str]:
         for phone in pinyin(text, style=Style.TONE3)
         for p in [
             get_initials(phone[0], strict=True),
-            get_finals(phone[0], strict=True),
+            # When using the new pypinyin, the previous code will drop the finals
+            get_finals(phone[0][:-1], strict=True) + phone[0][-1] if  phone[0][-1].isdigit() else get_finals(phone[0], strict=True),
         ]
-        if len(p) != 0
+        # Remove the case of individual tones as a phoneme
+        if len(p) != 0 and not p.isdigit()
     ]
     return phones