setup jamo

游雁

2023-11-24 b5d3df75cf6462aa3bf42fd3c86fa2aa7f1c8a15

 funasr/datasets/large_datasets/dataset.py

@@ -7,7 +7,8 @@
import torch.distributed as dist
import torchaudio
import numpy as np
import soundfile
# import librosa
import librosa
from kaldiio import ReadHelper
from torch.utils.data import IterableDataset

@@ -128,7 +129,8 @@
                        try:
                            waveform, sampling_rate = torchaudio.load(path)
                        except:
                            waveform, sampling_rate = soundfile.read(path, dtype='float32')
                            # waveform, sampling_rate = librosa.load(path, dtype='float32')
                            waveform, sampling_rate = librosa.load(path, dtype='float32')
                            if waveform.ndim == 2:
                                waveform = waveform[:, 0]
                            waveform = np.expand_dims(waveform, axis=0)