From fae856e23d45fd27d5fd55fd036e8e3fc7b24915 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期五, 02 六月 2023 23:00:08 +0800
Subject: [PATCH] update funasr-onnx-offline
---
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 f0f0c66..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)
--
Gitblit v1.9.1