From 24f73665e2d8ea8e4de2fe4f900bc539d7f7b989 Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期一, 17 四月 2023 15:49:45 +0800
Subject: [PATCH] Merge pull request #367 from alibaba-damo-academy/dev_lhn2
---
funasr/datasets/large_datasets/utils/tokenize.py | 6 +++---
1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index 3f20c5f..5a2f921 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -37,7 +37,7 @@
vad = -2
if bpe_tokenizer is not None:
- text = bpe_tokenizer.text2tokens(text)
+ text = bpe_tokenizer.text2tokens("".join(text))
if seg_dict is not None:
assert isinstance(seg_dict, dict)
@@ -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