def test_file_object(self):
np_audio = self.create_np_audio()
_, tmp_file = tempfile.mkstemp()
self.write_wave_file(np_audio, tmp_file)
class GFileWithSeekOnRead(tf.io.gfile.GFile):
"""Wrapper around GFile which is reusable across multiple read() calls.
This is needed because assertFeature reuses the same
FeatureExpectationItem several times.
"""
def read(self, *args, **kwargs):
data_read = super(GFileWithSeekOnRead, self).read(*args, **kwargs)
self.seek(0)
return data_read
with GFileWithSeekOnRead(tmp_file, "rb") as file_obj:
self.assertFeature(
feature=features.Audio(file_format="wav"),
shape=(None,),
dtype=tf.int64,
tests=[
testing.FeatureExpectationItem(
value=file_obj,
expected=np_audio,
),
],
)
def expectations(self):
np_audio = np.random.randint(-2**10,
2**10,
size=(10, ),
dtype=np.int64)
audio = pydub.AudioSegment.empty().set_sample_width(2)
# See documentation for _spawn usage:
# https://github.com/jiaaro/pydub/blob/master/API.markdown#audiosegmentget_array_of_samples
audio = audio._spawn(array.array(audio.array_type, np_audio))
_, tmp_file = tempfile.mkstemp()
audio.export(tmp_file, format="wav")
return [
# Numpy array
test_utils.FeatureExpectation(
name="audio_np",
feature=features.Audio(),
shape=(None, ),
dtype=tf.int64,
tests=[
test_utils.FeatureExpectationItem(
value=np_audio,
expected=np_audio,
),
],
),
# WAV file
test_utils.FeatureExpectation(
name="audio_np",
feature=features.Audio(file_format="wav"),
shape=(None, ),
dtype=tf.int64,
tests=[
test_utils.FeatureExpectationItem(
value=tmp_file,
expected=np_audio,
),
],
),
]
def test_numpy_array_float(self):
np_audio = self.create_np_audio().astype(np.float32)
self.assertFeature(
feature=features.Audio(dtype=tf.float32),
shape=(None,),
dtype=tf.float32,
tests=[
testing.FeatureExpectationItem(
value=np_audio,
expected=np_audio,
),
],
)
def test_numpy_array(self):
np_audio = self.create_np_audio()
self.assertFeature(
feature=features.Audio(),
shape=(None,),
dtype=tf.int64,
tests=[
testing.FeatureExpectationItem(
value=np_audio,
expected=np_audio,
),
],
)
def test_numpy_array_float(self, num_channels):
np_audio = _create_np_audio(num_channels).astype(np.float32)
self.assertFeature(
feature=features.Audio(dtype=tf.float32,
shape=_shape_for_channels(num_channels)),
shape=_shape_for_channels(num_channels),
dtype=tf.float32,
tests=[
testing.FeatureExpectationItem(
value=np_audio,
expected=np_audio,
),
],
)
def test_numpy_array(self):
np_audio = self.create_np_audio()
self.assertFeature(feature=features.Audio(sample_rate=1000),
shape=(None, ),
dtype=tf.int64,
tests=[
testing.FeatureExpectationItem(
value=np_audio,
expected=np_audio,
),
],
test_attributes=dict(
_file_format=None,
sample_rate=1000,
))
def test_wav_file(self):
np_audio = self.create_np_audio()
_, tmp_file = tempfile.mkstemp()
self.write_wave_file(np_audio, tmp_file)
self.assertFeature(feature=features.Audio(file_format="wav"),
shape=(None, ),
dtype=tf.int64,
tests=[
testing.FeatureExpectationItem(
value=tmp_file,
expected=np_audio,
),
],
test_attributes=dict(_file_format="wav", ))
def test_wav_file(self, num_channels):
np_audio = _create_np_audio(num_channels)
_, tmp_file = tempfile.mkstemp()
_write_wave_file(np_audio, tmp_file)
self.assertFeature(feature=features.Audio(
file_format='wav', shape=_shape_for_channels(num_channels)),
shape=_shape_for_channels(num_channels),
dtype=tf.int64,
tests=[
testing.FeatureExpectationItem(
value=tmp_file,
expected=np_audio,
),
testing.FeatureExpectationItem(
value=pathlib.Path(tmp_file),
expected=np_audio,
),
],
test_attributes=dict(_file_format='wav', ))
def test_sample_rate_property(self): self.assertEqual(features.Audio(sample_rate=1600).sample_rate, 1600)
