From 4aedebc3cd768527da7a8447c591956d7cb02c0a Mon Sep 17 00:00:00 2001
From: 仁迷 <haoneng.lhn@alibaba-inc.com>
Date: 星期二, 14 二月 2023 11:30:42 +0800
Subject: [PATCH] fix persian text segment bug
---
funasr/datasets/preprocessor.py | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/funasr/datasets/preprocessor.py b/funasr/datasets/preprocessor.py
index 10fbccb..d35d87f 100644
--- a/funasr/datasets/preprocessor.py
+++ b/funasr/datasets/preprocessor.py
@@ -354,7 +354,7 @@
if self.split_with_space:
tokens = text.strip().split(" ")
if self.seg_dict is not None:
- tokens = forward_segment("".join(tokens).lower(), self.seg_dict)
+ tokens = forward_segment("".join(tokens), self.seg_dict)
tokens = seg_tokenize(tokens, self.seg_dict)
else:
tokens = self.tokenizer.text2tokens(text)
--
Gitblit v1.9.1