From 219c2482ab755fbd4e49dfbdee91bf1a8a4ec49a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 19 五月 2023 11:33:27 +0800
Subject: [PATCH] websocket 2pass bugfix

---
 funasr/fileio/sound_scp.py |    9 ++++++---
 1 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/funasr/fileio/sound_scp.py b/funasr/fileio/sound_scp.py
index fc2c3e3..c752fe6 100644
--- a/funasr/fileio/sound_scp.py
+++ b/funasr/fileio/sound_scp.py
@@ -52,11 +52,11 @@
         if self.normalize:
             # soundfile.read normalizes data to [-1,1] if dtype is not given
             array, rate = librosa.load(
-                wav, sr=self.dest_sample_rate, mono=not self.always_2d
+                wav, sr=self.dest_sample_rate, mono=self.always_2d
             )
         else:
             array, rate = librosa.load(
-                wav, sr=self.dest_sample_rate, mono=not self.always_2d, dtype=self.dtype
+                wav, sr=self.dest_sample_rate, mono=self.always_2d, dtype=self.dtype
             )
 
         if self.speed_perturb is not None:
@@ -65,7 +65,10 @@
                 array, _ = torchaudio.sox_effects.apply_effects_tensor(
                     torch.tensor(array).view(1, -1), rate,
                     [['speed', str(speed)], ['rate', str(rate)]])
-            array = array.view(-1).numpy()
+                array = array.view(-1).numpy()
+
+        if array.ndim==2:
+            array=array.transpose((1, 0))
 
         return rate, array
 

--
Gitblit v1.9.1