From 7263fb08e9170e90e67cb9b48884cc6a35cb3b62 Mon Sep 17 00:00:00 2001
From: Haitao <chenht2010@hotmail.com>
Date: 星期五, 13 十二月 2024 13:47:15 +0800
Subject: [PATCH] 识别结果中有英语时,缺少空格或者第一个单词的问题 (#2284)
---
funasr/tokenizer/abs_tokenizer.py | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/funasr/tokenizer/abs_tokenizer.py b/funasr/tokenizer/abs_tokenizer.py
index a629e94..e125d29 100644
--- a/funasr/tokenizer/abs_tokenizer.py
+++ b/funasr/tokenizer/abs_tokenizer.py
@@ -62,7 +62,7 @@
raise RuntimeError(f"Unknown symbol '{unk_symbol}' doesn't exist in the token_list")
self.unk_id = self.token2id[self.unk_symbol]
- def encode(self, text):
+ def encode(self, text, **kwargs):
tokens = self.text2tokens(text)
text_ints = self.tokens2ids(tokens)
--
Gitblit v1.9.1