From 3705de9087ca7984077abce7a58df1fd042cffee Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=8D=97=E6=A0=96?=
 <76865636+Minami-su@users.noreply.github.com>
Date: Sat, 4 Nov 2023 16:47:46 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E5=A4=8D=E9=83=A8=E5=88=86=E6=97=A5?=
 =?UTF-8?q?=E6=96=87=E6=B1=89=E5=AD=97=E6=97=A0=E6=B3=95=E8=A2=AB=E6=8E=A8?=
 =?UTF-8?q?=E7=90=86/=E8=AE=AD=E7=BB=83=20(#148)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Update japanese.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
---
 text/japanese.py | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/text/japanese.py b/text/japanese.py
index 31cdf45..dde314d 100644
--- a/text/japanese.py
+++ b/text/japanese.py
@@ -361,7 +361,16 @@ def align_tones(phones, tones):
     return res
 
 
+import pykakasi
+
+kks = pykakasi.kakasi()
+
+
 def g2p(norm_text):
+    result = kks.convert(norm_text)
+    norm_text = ""
+    for i in result:
+        norm_text += i["hira"]
     sep_text, sep_kata, acc = text2sep_kata(norm_text)
     sep_tokenized = [tokenizer.tokenize(i) for i in sep_text]
     sep_phonemes = handle_long([kata2phoneme(i) for i in sep_kata])