From 27d2d3ccb7f64a5b21407adc6fd7ec0bddf0941d Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 12 四月 2024 15:30:03 +0800
Subject: [PATCH] add
---
funasr/tokenizer/char_tokenizer.py | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/funasr/tokenizer/char_tokenizer.py b/funasr/tokenizer/char_tokenizer.py
index 28b4f40..2efc0b0 100644
--- a/funasr/tokenizer/char_tokenizer.py
+++ b/funasr/tokenizer/char_tokenizer.py
@@ -36,6 +36,7 @@
self.remove_non_linguistic_symbols = remove_non_linguistic_symbols
self.split_with_space = split_with_space
self.seg_dict = None
+ seg_dict = seg_dict if seg_dict is not None else kwargs.get("seg_dict_file", None)
if seg_dict is not None:
self.seg_dict = load_seg_dict(seg_dict)
--
Gitblit v1.9.1