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
