From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
funasr/datasets/sense_voice_datasets/datasets.py | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/datasets/sense_voice_datasets/datasets.py b/funasr/datasets/sense_voice_datasets/datasets.py
index 20232cc..2e0266e 100644
--- a/funasr/datasets/sense_voice_datasets/datasets.py
+++ b/funasr/datasets/sense_voice_datasets/datasets.py
@@ -325,8 +325,8 @@
asr_target = item["target"]
if self.preprocessor_text:
asr_target = self.preprocessor_text(asr_target)
- emo_target = item["emo_target"]
- event_target = item["event_target"]
+ emo_target = item.get("emo_target", "<|NEUTRAL|>")
+ event_target = item.get("event_target", "<|Speech|>")
text_language = item.get("text_language", "<|zh|>")
punc_itn_bottom = item.get("with_or_wo_itn", "<|woitn|>")
--
Gitblit v1.9.1