From 3d9f094e9652d4b84894c6fd4eae39a4a753b0f0 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 五月 2023 23:48:00 +0800
Subject: [PATCH] train
---
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 f8833b1..cf7d255 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -48,7 +48,7 @@
vad = -2
if bpe_tokenizer is not None:
- text = bpe_tokenizer.text2tokens("".join(text))
+ text = bpe_tokenizer.text2tokens(text)
if seg_dict is not None:
assert isinstance(seg_dict, dict)
@@ -57,7 +57,7 @@
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