From 6e69d784e4814c3dbe35e8f70c6cf4b920c8b20b Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 19 三月 2025 23:10:13 +0800
Subject: [PATCH] 1. bug fix:list(mean)和list(var)，由于mean和var是numpy，导致写入到文件的格式错误，参考上面的话，大概率是list(mean.tolist())，其实外层list没有必要 (#2437)
---
funasr/tokenizer/char_tokenizer.py | 2 --
1 files changed, 0 insertions(+), 2 deletions(-)
diff --git a/funasr/tokenizer/char_tokenizer.py b/funasr/tokenizer/char_tokenizer.py
index 805ecd0..7b517da 100644
--- a/funasr/tokenizer/char_tokenizer.py
+++ b/funasr/tokenizer/char_tokenizer.py
@@ -50,9 +50,7 @@
)
def text2tokens(self, line: Union[str, list]) -> List[str]:
-
# if self.split_with_space:
-
if self.seg_dict is not None:
tokens = line.strip().split(" ")
tokens = seg_tokenize(tokens, self.seg_dict)
--
Gitblit v1.9.1