From fce4e1d1b48f23cd8332e60afce3df8d6209a6a7 Mon Sep 17 00:00:00 2001
From: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Date: 星期四, 11 四月 2024 14:59:22 +0800
Subject: [PATCH] SenseVoice对富文本解码的参数 (#1608)
---
funasr/datasets/audio_datasets/scp2jsonl.py | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/funasr/datasets/audio_datasets/scp2jsonl.py b/funasr/datasets/audio_datasets/scp2jsonl.py
index a537127..0764298 100644
--- a/funasr/datasets/audio_datasets/scp2jsonl.py
+++ b/funasr/datasets/audio_datasets/scp2jsonl.py
@@ -68,7 +68,7 @@
if os.path.exists(line):
waveform, _ = librosa.load(line, sr=16000)
sample_num = len(waveform)
- context_len = int(sample_num//16000*1000/10)
+ context_len = int(sample_num/16000*1000/10)
else:
context_len = len(line.split()) if " " in line else len(line)
res[key] = {data_type: line, f"{data_type}_len": context_len}
--
Gitblit v1.9.1