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/word_tokenizer.py | 4 +---
1 files changed, 1 insertions(+), 3 deletions(-)
diff --git a/funasr/tokenizer/word_tokenizer.py b/funasr/tokenizer/word_tokenizer.py
index d7bbaf9..c1fd6e0 100644
--- a/funasr/tokenizer/word_tokenizer.py
+++ b/funasr/tokenizer/word_tokenizer.py
@@ -14,14 +14,12 @@
delimiter: str = None,
non_linguistic_symbols: Union[Path, str, Iterable[str]] = None,
remove_non_linguistic_symbols: bool = False,
- **kwargs,
):
self.delimiter = delimiter
if not remove_non_linguistic_symbols and non_linguistic_symbols is not None:
warnings.warn(
- "non_linguistic_symbols is only used "
- "when remove_non_linguistic_symbols = True"
+ "non_linguistic_symbols is only used " "when remove_non_linguistic_symbols = True"
)
if non_linguistic_symbols is None:
--
Gitblit v1.9.1