From 54931dd4e1a099d7d6f144c4e12e5453deb3aa26 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期三, 28 六月 2023 10:41:57 +0800
Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into main
---
funasr/datasets/large_datasets/utils/tokenize.py | 6 ++----
1 files changed, 2 insertions(+), 4 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index f8833b1..a7eb6d2 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -46,10 +46,8 @@
text = data["text"]
token = []
vad = -2
-
if bpe_tokenizer is not None:
- text = bpe_tokenizer.text2tokens("".join(text))
-
+ text = bpe_tokenizer.text2tokens(" ".join(text))
if seg_dict is not None:
assert isinstance(seg_dict, dict)
text = seg_tokenize(text, seg_dict)
@@ -57,7 +55,7 @@
length = len(text)
if 'hw_tag' in data:
hotword_indxs = sample_hotword(length, **hw_config)
- data[hotword_indxs] = hotword_indxs
+ data['hotword_indxs'] = hotword_indxs
del data['hw_tag']
for i in range(length):
x = text[i]
--
Gitblit v1.9.1