From 50269e8b4dd0696d02e5da9f70c2d7952a26f392 Mon Sep 17 00:00:00 2001
From: WeiGodHorse <weigodhorse@gmail.com>
Date: Fri, 25 Mar 2022 22:58:41 +0800
Subject: [PATCH] fix a bug in Mandarin pypinyin_g2p_phone

---
 espnet2/text/phoneme_tokenizer.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/espnet2/text/phoneme_tokenizer.py b/espnet2/text/phoneme_tokenizer.py
index e6791d1818c..3af10ac6b94 100644
--- 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