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
)
def test_padding_issue_478():
"""
https://github.com/lhotse-speech/lhotse/issues/478
"""
with NamedTemporaryFile(suffix=".h5") as f, NumpyHdf5Writer(
f.name) as writer:
# Prepare data for cut 1.
cut1 = MonoCut("c1",
start=0,
duration=4.9,
channel=0,
recording=dummy_recording(1))
ali1 = np.random.randint(500, size=(121, ))
cut1.label_alignment = writer.store_array("c1",
ali1,
frame_shift=0.04,
temporal_dim=0)
# Prepare data for cut 2.
cut2 = MonoCut("c2",
start=0,
duration=4.895,
channel=0,
recording=dummy_recording(2))
ali2 = np.random.randint(500, size=(121, ))
cut2.label_alignment = writer.store_array("c2",
ali2,
frame_shift=0.04,
temporal_dim=0)
# Test collation behavior on this cutset.
cuts = CutSet.from_cuts([cut1, cut2])
label_alignments, label_alignment_lens = collate_custom_field(
cuts, "label_alignment")
np.testing.assert_equal(label_alignments[0].numpy(), ali1)
np.testing.assert_equal(label_alignments[1].numpy(), ali2)
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_collate_custom_temporal_array_ints(pad_direction):
CODEBOOK_SIZE = 512
FRAME_SHIFT = 0.04
EXPECTED_PAD_VALUE = 0
cuts = CutSet.from_json("test/fixtures/ljspeech/cuts.json")
max_num_frames = max(
seconds_to_frames(cut.duration, FRAME_SHIFT) for cut in cuts)
with NamedTemporaryFile(suffix=".h5") as f, NumpyHdf5Writer(
f.name) as writer:
expected_codebook_indices = []
for cut in cuts:
expected_codebook_indices.append(
np.random.randint(CODEBOOK_SIZE,
size=(seconds_to_frames(
cut.duration,
FRAME_SHIFT), )).astype(np.int16))
cut.codebook_indices = writer.store_array(
cut.id,
expected_codebook_indices[-1],
frame_shift=FRAME_SHIFT,
temporal_dim=0,
)
codebook_indices, codebook_indices_lens = collate_custom_field(
cuts, "codebook_indices", pad_direction=pad_direction)
assert isinstance(codebook_indices_lens, torch.Tensor)
assert codebook_indices_lens.dtype == torch.int32
assert codebook_indices_lens.shape == (len(cuts), )
assert codebook_indices_lens.tolist() == [
seconds_to_frames(c.duration, FRAME_SHIFT) for c in cuts
]
assert isinstance(codebook_indices, torch.Tensor)
assert (codebook_indices.dtype == torch.int64
) # the dtype got promoted by default
assert codebook_indices.shape == (len(cuts), max_num_frames)
for idx, cbidxs in enumerate(expected_codebook_indices):
exp_len = cbidxs.shape[0]
# PyTorch < 1.9.0 doesn't have an assert_equal function.
if pad_direction == "right":
np.testing.assert_equal(
codebook_indices[idx, :exp_len].numpy(), cbidxs)
np.testing.assert_equal(
codebook_indices[idx, exp_len:].numpy(),
EXPECTED_PAD_VALUE)
if pad_direction == "left":
np.testing.assert_equal(
codebook_indices[idx, -exp_len:].numpy(), cbidxs)
np.testing.assert_equal(
codebook_indices[idx, :-exp_len].numpy(),
EXPECTED_PAD_VALUE)
if pad_direction == "both":
half = (max_num_frames - exp_len) // 2
np.testing.assert_equal(codebook_indices[idx, :half].numpy(),
EXPECTED_PAD_VALUE)
np.testing.assert_equal(
codebook_indices[idx, half:half + exp_len].numpy(), cbidxs)
if half > 0:
# indexing like [idx, -0:] would return the whole array rather
# than an empty slice.
np.testing.assert_equal(
codebook_indices[idx, -half:].numpy(),
EXPECTED_PAD_VALUE)