0.2.1

游雁

2023-02-22 4d914ceba7e2e7b18f811fab77205b6d6b6c55d0

 funasr/datasets/large_datasets/dataset.py

@@ -1,6 +1,6 @@
import os
import random
import soundfile
import numpy
from functools import partial

import torch
@@ -119,6 +119,7 @@
                    elif data_type == "sound":
                        key, path = item.strip().split()
                        waveform, sampling_rate = torchaudio.load(path)
                        waveform = waveform.numpy()
                        mat = waveform[0]
                        sample_dict[data_name] = mat
                        sample_dict["sampling_rate"] = sampling_rate