From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
funasr/tokenizer/korean_cleaner.py | 7 ++-----
1 files changed, 2 insertions(+), 5 deletions(-)
diff --git a/funasr/tokenizer/korean_cleaner.py b/funasr/tokenizer/korean_cleaner.py
index ee556d4..eceebe2 100644
--- a/funasr/tokenizer/korean_cleaner.py
+++ b/funasr/tokenizer/korean_cleaner.py
@@ -19,8 +19,7 @@
"9": "甑�",
}
new_text = "".join(
- number_to_kor[char] if char in number_to_kor.keys() else char
- for char in text
+ number_to_kor[char] if char in number_to_kor.keys() else char for char in text
)
return new_text
@@ -56,9 +55,7 @@
}
new_text = re.sub("[a-z]+", lambda x: str.upper(x.group()), text)
new_text = "".join(
- upper_alphabet_to_kor[char]
- if char in upper_alphabet_to_kor.keys()
- else char
+ upper_alphabet_to_kor[char] if char in upper_alphabet_to_kor.keys() else char
for char in new_text
)
--
Gitblit v1.9.1