def test_cut_load_custom_recording_truncate():
sampling_rate = 16000
duration = 52.4
audio = np.random.randn(1, compute_num_samples(duration, sampling_rate)).astype(
np.float32
)
audio /= np.abs(audio).max() # normalize to [-1, 1]
with NamedTemporaryFile(suffix=".wav") as f:
torchaudio.save(f.name, torch.from_numpy(audio), sampling_rate)
f.flush()
os.fsync(f)
recording = Recording.from_file(f.name)
# Note: MonoCut doesn't normally have an "alignment" attribute,
# and a "load_alignment()" method.
# We are dynamically extending it.
cut = MonoCut(id="x", start=0, duration=duration, channel=0)
cut.my_favorite_song = recording
cut_trunc = cut.truncate(duration=5.0)
restored_audio = cut_trunc.load_my_favorite_song()
assert restored_audio.shape == (1, 80000)
np.testing.assert_almost_equal(audio[:, :80000], restored_audio)
def test_cut_load_array_truncate():
"""Check that loading a custom Array works after truncation."""
ivector = np.arange(20).astype(np.float32)
with NamedTemporaryFile(suffix=".h5") as f, LilcomHdf5Writer(f.name) as writer:
cut = MonoCut(id="x", start=0, duration=5, channel=0)
cut.ivector = writer.store_array(key="utt1", value=ivector)
cut = cut.truncate(duration=3)
restored_ivector = cut.load_ivector()
np.testing.assert_equal(ivector, restored_ivector)
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)
