From 09c472ea9ebe50af83321aaa7a1d49bd1c64a076 Mon Sep 17 00:00:00 2001
From: duliangang <duliangang@gmail.com>
Date: Sun, 28 Jan 2024 16:28:24 +0800
Subject: [PATCH] fix chinese number to pinyin
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

数字转拼音不准的bug，因为将数字一个个分割了调用an2cn当然不准
---
 GPT_SoVITS/text/chinese.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/GPT_SoVITS/text/chinese.py b/GPT_SoVITS/text/chinese.py
index de3ef01..bb631a0 100644
--- a/GPT_SoVITS/text/chinese.py
+++ b/GPT_SoVITS/text/chinese.py
@@ -12,6 +12,8 @@ sys.path.append("/data/docker/liujing04/gpt-vits/gpt-vits-master")
 from text.symbols import punctuation
 from text.tone_sandhi import ToneSandhi
 
+normalizer = lambda x: cn2an.transform(x, "an2cn")
+
 current_file_path = os.path.dirname(__file__)
 pinyin_to_symbol_map = {
     line.split("\t")[0]: line.strip().split("\t")[1]
@@ -151,10 +153,8 @@ def _g2p(segments):
 
 
 def text_normalize(text):
-    numbers = re.findall(r"\d+(?:\.?\d+)?", text)
-    for number in numbers:
-        text = text.replace(number, cn2an.an2cn(number), 1)
-    text = replace_punctuation(text)
+    dest_text=normalizer(text)
+    text = replace_punctuation(dest_text)
 
     return text