egs/wenetspeech/conformer/local/process_opus.py
@@ -65,7 +65,7 @@ start = int(start_time_list[i] * sample_rate) end = int(end_time_list[i] * sample_rate) target_audio = waveform[:, start:end].transpose(0, 1).contiguous() target_audio = waveform[:, start:end] torchaudio.save(seg_wav_path, target_audio, sample_rate) fout.write("{} {}\n".format(utt_id, seg_wav_path))
