funasr/fileio/sound_scp.py
@@ -4,7 +4,7 @@ import random import numpy as np import soundfile import librosa import librosa import torch @@ -116,7 +116,7 @@ def __getitem__(self, key): wav = self.data[key] if self.normalize: # soundfile.read normalizes data to [-1,1] if dtype is not given # librosa.load normalizes data to [-1,1] if dtype is not given array, rate = librosa.load( wav, sr=self.dest_sample_rate, mono=self.always_2d )
