From 3c349ac0531b07239f37b81254f8568ab80e3f6a Mon Sep 17 00:00:00 2001
From: Han Zhang <45134013+holazzer@users.noreply.github.com>
Date: 星期二, 18 三月 2025 11:45:37 +0800
Subject: [PATCH] fix: use converted token_ids for alignment for sensevoice model with timestamp output (#2429)
---
funasr/utils/timestamp_tools.py | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.py
index 995e179..37ce886 100644
--- a/funasr/utils/timestamp_tools.py
+++ b/funasr/utils/timestamp_tools.py
@@ -160,7 +160,7 @@
punc_id = int(punc_id) if punc_id is not None else 1
sentence_end = timestamp[1] if timestamp is not None else sentence_end
sentence_text_seg = (
- sentence_text_seg[:-1] if sentence_text_seg[-1] == " " else sentence_text_seg
+ sentence_text_seg[:-1] if sentence_text_seg and sentence_text_seg[-1] == " " else sentence_text_seg
)
if punc_id > 1:
sentence_text += punc_list[punc_id - 2]
--
Gitblit v1.9.1