From 561bdbdfc0f8fd6234c5130fdc8631bf8e294bd8 Mon Sep 17 00:00:00 2001
From: 王梦迪 <73778524+di-osc@users.noreply.github.com>
Date: 星期四, 22 五月 2025 11:27:01 +0800
Subject: [PATCH] 通过缓存seg_dict，加快seaco_paraformer推理 (#2520)
---
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