From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
funasr/tokenizer/sentencepiece_tokenizer.py | 6 ++++++
1 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/funasr/tokenizer/sentencepiece_tokenizer.py b/funasr/tokenizer/sentencepiece_tokenizer.py
index 1be1b81..0b47a9f 100644
--- a/funasr/tokenizer/sentencepiece_tokenizer.py
+++ b/funasr/tokenizer/sentencepiece_tokenizer.py
@@ -49,3 +49,9 @@
def get_vocab_size(self):
return self.sp.GetPieceSize()
+
+ def ids2tokens(self, *args, **kwargs):
+ return self.decode(*args, **kwargs)
+
+ def tokens2ids(self, *args, **kwargs):
+ return self.encode(*args, **kwargs)
--
Gitblit v1.9.1