def test_invariants_pad(self, sampling_rate: int, window_hop: int,
pad_direction: str, rand_gen):
# Generate cut duration in numbers of samples
num_samples = rand_gen.draw(
st.integers(round(sampling_rate * 0.46),
round(sampling_rate * 1.9)),
label="Number of audio samples in a cut.",
)
# Generate random cut
frame_shift = window_hop / sampling_rate
cut = self.with_cut(
sampling_rate=sampling_rate,
num_samples=num_samples,
frame_shift=frame_shift,
features=False,
custom_field=True,
)
# Pad with random duration
duration = rand_gen.draw(
st.floats(min_value=cut.duration + 0.03 * cut.duration,
max_value=cut.duration * 2),
label=f"Padded cut duration",
)
padded = cut.pad(
duration=duration,
direction=pad_direction,
pad_value_dict={"codebook_indices": -1},
)
# Test the invariants
array = padded.load_codebook_indices()
assert array.ndim == padded.codebook_indices.ndim
expected_num_frames = seconds_to_frames(
padded.duration, padded.codebook_indices.frame_shift)
assert array.shape[0] == expected_num_frames
self.cleanup()
def test_collate_custom_temporal_array_ints(pad_value):
CODEBOOK_SIZE = 512
FRAME_SHIFT = 0.04
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_value=pad_value)
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.int16
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.
np.testing.assert_equal(codebook_indices[idx, :exp_len].numpy(),
cbidxs)
expected_pad_value = 0 if pad_value is None else pad_value
np.testing.assert_equal(codebook_indices[idx, exp_len:].numpy(),
expected_pad_value)
def _with_custom_temporal_array(self, cut: MonoCut, frame_shift: Seconds) -> None:
d = TemporaryDirectory()
self.dirs.append(d)
num_frames = seconds_to_frames(cut.duration, frame_shift=frame_shift)
array = np.random.randint(256, size=(num_frames,))
with NumpyHdf5Writer(d.name) as storage:
cut.codebook_indices = storage.store_array(
key="ali1", value=array, frame_shift=frame_shift, temporal_dim=0
)
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)