LoadAudio(),
MapLabels(class_map=class_map),
MixUp(p=args.p_mixup),
STFT(n_fft=config.data.n_fft,
hop_size=config.data.hop_size),
DropFields(("audio", "filename", "sr")),
RenameFields({"stft": "signal"})
]),
clean_transform=Compose([
LoadAudio(),
MapLabels(class_map=class_map),
])),
shuffle=True,
drop_last=True,
batch_size=config.train.batch_size,
collate_fn=make_collate_fn({"signal": math.log(STFT.eps)}),
**loader_kwargs)
valid_loader = torch.utils.data.DataLoader(
SoundDataset(audio_files=[
os.path.join(args.train_data_dir, fname)
for fname in train_df.fname.values[valid]
],
labels=[
item.split(",")
for item in train_df.labels.values[valid]
],
transform=Compose([
LoadAudio(),
MapLabels(class_map=class_map),
STFT(n_fft=config.data.n_fft,
transform=Compose([
LoadAudio(),
SampleLongAudio(max_length=args.max_audio_length),
MixUp(p=args.p_mixup),
AudioAugmentation(p=args.p_aug),
audio_transform,
DropFields(("audio", "sr")),
]),
clean_transform=Compose([
LoadAudio(),
SampleLongAudio(max_length=args.max_audio_length)
])),
shuffle=True,
drop_last=True,
batch_size=config.train.batch_size,
collate_fn=make_collate_fn(
{"signal": audio_transform.padding_value}),
**loader_kwargs)
valid_loader = torch.utils.data.DataLoader(
AntispoofDataset(audio_files=[
os.path.join(args.train_data_dir, fname)
for fname in train_df.fname.values[valid]
],
labels=train_df.labels.values[valid],
transform=Compose([
LoadAudio(),
audio_transform,
DropFields(("audio", "sr")),
])),
shuffle=False,
batch_size=config.train.batch_size,
