From 556429d8a98fcab3e77ce1a0d5e7163691643872 Mon Sep 17 00:00:00 2001
From: aky15 <ankeyuthu@gmail.com>
Date: 星期二, 30 五月 2023 16:39:22 +0800
Subject: [PATCH] Dev aky2 (#559)
---
funasr/datasets/large_datasets/utils/tokenize.py | 4 +---
1 files changed, 1 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index cf7d255..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(text)
-
+ text = bpe_tokenizer.text2tokens(" ".join(text))
if seg_dict is not None:
assert isinstance(seg_dict, dict)
text = seg_tokenize(text, seg_dict)
--
Gitblit v1.9.1