def init_weight(weights, initializer):
"""Helper function for initialization of the weight tensor.
This function accepts several types of initializer, prepares
the appropriate ``~chainer.Initializer`` if necessary,
and does the initialization.
Args:
weights (numpy.ndarray or cupy.ndarray):
Weight tensor to be initialized.
initializer: The value used to initialize the data.
May be ``None`` (in which case
:class:`~chainer.initializers.HeNormal`
is used as an initializer), a scalar to set all values to,
an ``numpy.ndarray`` to be assigned,
or a callable that takes :class:`numpy.ndarray`
or :class:`cupy.ndarray` and edits its value.
"""
if initializer is None:
initializer = HeNormal(1 / numpy.sqrt(2))
elif numpy.isscalar(initializer):
initializer = Constant(initializer)
elif isinstance(initializer, numpy.ndarray):
initializer = Constant(initializer)
assert callable(initializer)
initializer(weights)
def _get_initializer(initializer):
if initializer is None:
return HeNormal(1 / numpy.sqrt(2))
if numpy.isscalar(initializer):
return Constant(initializer)
if isinstance(initializer, numpy.ndarray):
return Constant(initializer)
assert callable(initializer)
return initializer
def _get_initializer(initializer):
if initializer is None:
return LeCunNormal()
if numpy.isscalar(initializer):
return Constant(initializer)
if isinstance(initializer, numpy.ndarray):
return Constant(initializer)
if not callable(initializer):
raise TypeError('invalid type of initializer: %s' % type(initializer))
return initializer
def _get_initializer(initializer, scale=1.0):
if initializer is None:
return HeNormal(scale / numpy.sqrt(2))
if numpy.isscalar(initializer):
return Constant(initializer * scale)
if isinstance(initializer, numpy.ndarray):
return Constant(initializer * scale)
assert callable(initializer)
if scale == 1.0:
return initializer
return _ScaledInitializer(initializer, scale)
def _get_initializer(initializer):
# type: (tp.Optional[types.InitializerSpec]) -> types.AbstractInitializer # NOQA
if initializer is None:
return LeCunNormal()
if numpy.isscalar(initializer):
return Constant(initializer)
if isinstance(initializer, numpy.ndarray):
return Constant(initializer)
if not callable(initializer):
raise TypeError('invalid type of initializer: %s' % type(initializer))
return initializer
def __init__(self,
sample_rate=16000,
window_size_sec=0.02,
window_stride_sec=0.01,
n_fft=512,
n_filters=64,
preemph=0.97,
dither=1.0e-05):
super(NemoMelSpecExtractor, self).__init__()
self.log_zero_guard_value = 2**-24
win_length = int(window_size_sec * sample_rate)
self.hop_length = int(window_stride_sec * sample_rate)
self.n_filters = n_filters
from scipy import signal as scipy_signal
from librosa import stft as librosa_stft
window_arr = scipy_signal.hann(win_length, sym=True)
self.stft = lambda x: librosa_stft(x,
n_fft=n_fft,
hop_length=self.hop_length,
win_length=win_length,
window=window_arr,
center=True)
self.dither = dither
self.preemph = preemph
self.pad_align = 16
from librosa.filters import mel as librosa_mel
self.fb_arr = librosa_mel(sample_rate,
n_fft,
n_mels=n_filters,
fmin=0,
fmax=(sample_rate / 2))
with self.init_scope():
self.window = initializers.generate_array(initializer=Constant(
0, dtype="float32"),
shape=window_arr.shape,
xp=self.xp,
dtype=np.float32)
self.register_persistent("window")
self.fb = initializers.generate_array(
initializer=Constant(0, dtype="float32"),
shape=np.expand_dims(self.fb_arr, axis=0).shape,
xp=self.xp,
dtype="float32")
self.register_persistent("fb")
def _get_initializer(
initializer: tp.Optional[types.InitializerSpec]
) -> types.AbstractInitializer:
if initializer is None:
return LeCunNormal()
if (isinstance(initializer, chainer.get_array_types())
or numpy.isscalar(initializer)):
return Constant(initializer)
if not callable(initializer):
raise TypeError('invalid type of initializer: %s' % type(initializer))
return initializer
