def __init__(self, filename, dtype=None):
"""AudioIODataset."""
with tf.name_scope("AudioIODataset"):
if not tf.executing_eagerly():
assert dtype is not None, "dtype must be provided in graph mode"
resource = core_ops.io_audio_readable_init(filename)
if tf.executing_eagerly():
shape, dtype, _ = core_ops.io_audio_readable_spec(resource)
dtype = tf.as_dtype(dtype.numpy())
else:
shape, _, _ = core_ops.io_audio_readable_spec(resource)
capacity = 1024 # kwargs.get("capacity", 4096)
self._resource = resource
dataset = tf.data.Dataset.range(0, shape[0], capacity)
dataset = dataset.map(
lambda index: core_ops.io_audio_readable_read(
resource, index, index + capacity, dtype=dtype
)
)
dataset = dataset.apply(
tf.data.experimental.take_while(lambda v: tf.greater(tf.shape(v)[0], 0))
)
dataset = dataset.unbatch()
self._dataset = dataset
super().__init__(
self._dataset._variant_tensor
) # pylint: disable=protected-access
def __init__(self, filename, dtype=None):
with tf.name_scope("AudioIOTensor"):
if not tf.executing_eagerly():
assert dtype is not None, "dtype must be provided in graph mode"
resource = core_ops.io_audio_readable_init(filename)
if tf.executing_eagerly():
shape, dtype, rate = core_ops.io_audio_readable_spec(resource)
dtype = tf.as_dtype(dtype.numpy())
else:
shape, _, rate = core_ops.io_audio_readable_spec(resource)
self._resource = resource
self._shape = shape
self._dtype = dtype
self._rate = rate
super().__init__()