From 810046e3df4910c8f5c1a90e4b53aca45b3397e8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期一, 01 七月 2024 10:42:58 +0800
Subject: [PATCH] 优化merge segments 参数，解决新闻联播男女主持人“晚上好”合并一个speakid问题 (#1861)
---
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