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/postprocess_utils.py | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/funasr/utils/postprocess_utils.py b/funasr/utils/postprocess_utils.py
index dcc713f..60ebb56 100644
--- a/funasr/utils/postprocess_utils.py
+++ b/funasr/utils/postprocess_utils.py
@@ -122,7 +122,7 @@
abbr_word += words[num].upper()
num += 1
word_lists.append(abbr_word)
- if time_stamp is not None:
+ if time_stamp is not None and ts_nums[num] < len(time_stamp):
end = time_stamp[ts_nums[num]][1]
ts_lists.append([begin, end])
else:
--
Gitblit v1.9.1