def test_padding_cut_audio_mask(self):
cut = PaddingCut('cut',
duration=2,
sampling_rate=16000,
use_log_energy=True,
num_samples=32000)
mask = cut.supervisions_audio_mask()
assert mask.sum() == 0
def test_padding_cut_audio_mask(self):
cut = PaddingCut('cut',
duration=2,
sampling_rate=16000,
feat_value=LOG_EPSILON,
num_samples=32000)
mask = cut.supervisions_audio_mask()
assert mask.sum() == 0
def test_padding_cut_perturb():
cut = PaddingCut(id='cut',
duration=5.75,
sampling_rate=16000,
feat_value=1e-10,
num_samples=92000)
cut_sp = cut.perturb_speed(1.1)
assert cut_sp.num_samples == 83636
assert cut_sp.duration == 5.22725
def test_padding_cut_perturb():
cut = PaddingCut(id='cut',
duration=5.75,
sampling_rate=16000,
use_log_energy=True,
num_samples=92000)
cut_sp = cut.perturb_speed(1.1)
assert cut_sp.num_samples == 83636
assert cut_sp.duration == 5.22725
def test_padding_cut_features_mask(self):
cut = PaddingCut('cut',
duration=2,
sampling_rate=16000,
feat_value=LOG_EPSILON,
num_frames=2000,
num_features=13)
mask = cut.supervisions_feature_mask()
assert mask.sum() == 0
def test_padding_cut_features_mask(self):
cut = PaddingCut('cut',
duration=2,
sampling_rate=16000,
use_log_energy=True,
num_frames=2000,
num_features=13)
mask = cut.supervisions_feature_mask()
assert mask.sum() == 0
def test_resample_padding_cut():
original = PaddingCut(id='cut',
duration=5.75,
sampling_rate=16000,
feat_value=1e-10,
num_samples=92000)
resampled = original.resample(8000)
assert resampled.sampling_rate == 8000
assert resampled.num_samples == original.num_samples / 2
samples = resampled.load_audio()
assert samples.shape[1] == resampled.num_samples
def test_padding_cut_perturb_volume():
cut = PaddingCut(
id="cut",
duration=5.75,
sampling_rate=16000,
feat_value=1e-10,
num_samples=92000,
)
cut_vp = cut.perturb_volume(0.125)
assert cut_vp.num_samples == cut.num_samples
assert cut_vp.duration == cut.duration
np.testing.assert_array_almost_equal(cut_vp.load_audio(), cut.load_audio())
def test_padding_cut_reverb_rir(rir):
cut = PaddingCut(
id="cut",
duration=5.75,
sampling_rate=16000,
feat_value=1e-10,
num_samples=92000,
)
cut_rvb = cut.reverb_rir(rir_recording=rir)
assert cut_rvb.num_samples == cut.num_samples
assert cut_rvb.duration == cut.duration
np.testing.assert_array_almost_equal(cut_rvb.load_audio(), cut.load_audio())
def padding_cut():
return PaddingCut(id='padding-1',
duration=10.0,
num_frames=1000,
num_features=40,
sampling_rate=16000,
num_samples=160000,
use_log_energy=True)
def padding_cut():
return PaddingCut(id='padding-1',
duration=10.0,
num_frames=1000,
num_features=40,
frame_shift=0.01,
sampling_rate=16000,
num_samples=160000,
feat_value=PADDING_LOG_ENERGY)
def padding_cut():
return PaddingCut(
id="padding-1",
duration=10.0,
num_frames=1000,
num_features=40,
frame_shift=0.01,
sampling_rate=16000,
num_samples=160000,
feat_value=LOG_EPSILON,
)
def cutset():
return CutSet.from_cuts([
# MonoCut
dummy_cut(0, supervisions=[dummy_supervision(0)]),
# PaddingCut
PaddingCut('pad', duration=1.0, sampling_rate=16000, feat_value=-100,
num_frames=100, frame_shift=0.01, num_features=80, num_samples=16000),
# MixedCut
dummy_cut(0, supervisions=[dummy_supervision(0)]).mix(
dummy_cut(1, supervisions=[dummy_supervision(1)]),
offset_other_by=0.5,
snr=10
)
])
import pytest
from lhotse import CutSet
from lhotse.cut import PaddingCut
from lhotse.testing.dummies import dummy_cut, dummy_supervision
parametrize_on_cut_types = pytest.mark.parametrize(
'cut', [
# MonoCut
dummy_cut(0, supervisions=[dummy_supervision(0)]),
# PaddingCut
PaddingCut('pad', duration=1.0, sampling_rate=16000, feat_value=-100,
num_frames=100, frame_shift=0.01, num_features=80, num_samples=16000),
# MixedCut
dummy_cut(0, supervisions=[dummy_supervision(0)]).mix(
dummy_cut(1, supervisions=[dummy_supervision(1)]),
offset_other_by=0.5,
snr=10
)
]
)
@parametrize_on_cut_types
def test_drop_features(cut):
assert cut.has_features
cut_drop = cut.drop_features()
assert cut.has_features
assert not cut_drop.has_features