From 33681507e1d3468f6a8670e82c47a1b69cb4a394 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 13 四月 2023 10:03:42 +0800
Subject: [PATCH] Merge pull request #342 from alibaba-damo-academy/dev_cmz
---
funasr/datasets/large_datasets/utils/tokenize.py | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index d8ceff2..5a2f921 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -47,8 +47,8 @@
length = len(text)
for i in range(length):
x = text[i]
- if i == length-1 and "punc" in data and text[i].startswith("vad:"):
- vad = x[-1][4:]
+ if i == length-1 and "punc" in data and x.startswith("vad:"):
+ vad = x[4:]
if len(vad) == 0:
vad = -1
else:
--
Gitblit v1.9.1