From 810046e3df4910c8f5c1a90e4b53aca45b3397e8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期一, 01 七月 2024 10:42:58 +0800
Subject: [PATCH] 优化merge segments 参数，解决新闻联播男女主持人“晚上好”合并一个speakid问题 (#1861)
---
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