From 172a3152b42af36443ec6a0a39969471c35b893d Mon Sep 17 00:00:00 2001
From: maliubiao <maliubiao@gmail.com>
Date: 星期日, 29 十二月 2024 22:33:22 +0800
Subject: [PATCH] 允许 model.generate 使用bytes io, 以便不写入文件，节省io时间 (#2343)
---
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