def test_cut_load_temporal_array():
"""Check that we can read a TemporalArray from a cut when their durations match."""
alignment = np.random.randint(500, size=131)
with NamedTemporaryFile(suffix=".h5") as f, NumpyHdf5Writer(f.name) as writer:
manifest = writer.store_array(
key="utt1", value=alignment, frame_shift=0.4, temporal_dim=0
)
expected_duration = 52.4 # 131 frames x 0.4s frame shift == 52.4s
cut = MonoCut(id="x", start=0, duration=expected_duration, channel=0)
# Note: MonoCut doesn't normally have an "alignment" attribute,
# and a "load_alignment()" method.
# We are dynamically extending it.
cut.alignment = manifest
restored_alignment = cut.load_alignment()
np.testing.assert_equal(alignment, restored_alignment)
def test_cut_load_temporal_array_truncate():
"""Check the array loaded via TemporalArray is truncated along with the cut."""
with NamedTemporaryFile(suffix=".h5") as f, NumpyHdf5Writer(f.name) as writer:
expected_duration = 52.4 # 131 frames x 0.4s frame shift == 52.4s
cut = MonoCut(id="x", start=0, duration=expected_duration, channel=0)
alignment = np.random.randint(500, size=131)
cut.alignment = writer.store_array(
key="utt1", value=alignment, frame_shift=0.4, temporal_dim=0
)
cut_trunc = cut.truncate(duration=5.0)
alignment_piece = cut_trunc.load_alignment()
assert alignment_piece.shape == (13,) # 5.0 / 0.4 == 12.5 ~= 13
np.testing.assert_equal(alignment[:13], alignment_piece)
def test_cut_load_temporal_array_pad(pad_value):
"""Check the array loaded via TemporalArray is padded along with the cut."""
with NamedTemporaryFile(suffix=".h5") as f, NumpyHdf5Writer(f.name) as writer:
cut = MonoCut(
id="x",
start=0,
duration=52.4, # 131 frames x 0.4s frame shift == 52.4s
channel=0,
recording=dummy_recording(1),
)
alignment = np.random.randint(500, size=131)
cut.alignment = writer.store_array(
key="utt1", value=alignment, frame_shift=0.4, temporal_dim=0
)
cut_pad = cut.pad(duration=60.0, pad_value_dict={"alignment": pad_value})
alignment_pad = cut_pad.load_alignment()
assert alignment_pad.shape == (150,) # 60.0 / 0.4 == 150
np.testing.assert_equal(alignment_pad[:131], alignment)
np.testing.assert_equal(alignment_pad[131:], pad_value)
def test_validate_cut_with_temporal_array(caplog):
# Note: "caplog" is a special variable in pytest that captures logs.
caplog.set_level(logging.WARNING)
with NamedTemporaryFile(suffix=".h5") as f, NumpyHdf5Writer(
f.name) as writer:
cut = MonoCut(
id="cut1",
start=0,
duration=4.9,
channel=0,
recording=dummy_recording(1),
)
alignment = np.random.randint(500, size=131)
cut.alignment = writer.store_array(key="utt1",
value=alignment,
frame_shift=0.4,
temporal_dim=0)
validate(cut)
assert ("MonoCut cut1: possibly mismatched duration between cut (4.9s) "
"and temporal array in custom field 'alignment' (num_frames=131 "
"* frame_shift=0.4 == duration=52.400000000000006)" in caplog.text)
