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/preprocessor.py |    4 +++-
 1 files changed, 3 insertions(+), 1 deletions(-)

diff --git a/funasr/datasets/audio_datasets/preprocessor.py b/funasr/datasets/audio_datasets/preprocessor.py
index c2e27bf..ab75140 100644
--- a/funasr/datasets/audio_datasets/preprocessor.py
+++ b/funasr/datasets/audio_datasets/preprocessor.py
@@ -26,8 +26,10 @@
 			return waveform
 		speed = random.choice(self.speed_perturb)
 		if speed != 1.0:
+			if not isinstance(waveform, torch.Tensor):
+				waveform = torch.tensor(waveform)
 			waveform, _ = torchaudio.sox_effects.apply_effects_tensor(
-				torch.tensor(waveform).view(1, -1), fs, [['speed', str(speed)], ['rate', str(fs)]])
+				waveform.view(1, -1), fs, [['speed', str(speed)], ['rate', str(fs)]])
 			waveform = waveform.view(-1)
 			
 		return waveform

--
Gitblit v1.9.1