From 7231fa07672ba276a7df937e27e2b813e653dd21 Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期六, 11 三月 2023 13:52:22 +0800
Subject: [PATCH] Merge pull request #213 from zhuzizyf/small-datatype-resample

---
 funasr/fileio/sound_scp.py |   11 ++++++++---
 1 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/funasr/fileio/sound_scp.py b/funasr/fileio/sound_scp.py
index 459369e..dc872b0 100644
--- a/funasr/fileio/sound_scp.py
+++ b/funasr/fileio/sound_scp.py
@@ -4,6 +4,7 @@
 
 import numpy as np
 import soundfile
+import librosa
 from typeguard import check_argument_types
 
 from funasr.fileio.read_text import read_2column_text
@@ -30,6 +31,7 @@
         dtype=np.int16,
         always_2d: bool = False,
         normalize: bool = False,
+        dest_sample_rate: int = 16000,
     ):
         assert check_argument_types()
         self.fname = fname
@@ -37,15 +39,18 @@
         self.always_2d = always_2d
         self.normalize = normalize
         self.data = read_2column_text(fname)
+        self.dest_sample_rate = dest_sample_rate
 
     def __getitem__(self, key):
         wav = self.data[key]
         if self.normalize:
             # soundfile.read normalizes data to [-1,1] if dtype is not given
-            array, rate = soundfile.read(wav, always_2d=self.always_2d)
+            array, rate = librosa.load(
+                wav, sr=self.dest_sample_rate, mono=not self.always_2d
+            )
         else:
-            array, rate = soundfile.read(
-                wav, dtype=self.dtype, always_2d=self.always_2d
+            array, rate = librosa.load(
+                wav, sr=self.dest_sample_rate, mono=not self.always_2d, dtype=self.dtype
             )
 
         return rate, array

--
Gitblit v1.9.1