def _create_network(self, vocab_size, num_conv_layers, num_rnn_layers,
rnn_layer_size, use_gru, share_rnn_weights):
"""Create data layers and model network."""
# paddle.data_type.dense_array is used for variable batch input.
# The size 161 * 161 is only an placeholder value and the real shape
# of input batch data will be induced during training.
audio_data = paddle.layer.data(name="audio_spectrogram",
type=paddle.data_type.dense_array(161 *
161))
text_data = paddle.layer.data(
name="transcript_text",
type=paddle.data_type.integer_value_sequence(vocab_size))
self._log_probs, self._loss = deep_speech_v2_network(
audio_data=audio_data,
text_data=text_data,
dict_size=vocab_size,
num_conv_layers=num_conv_layers,
num_rnn_layers=num_rnn_layers,
rnn_size=rnn_layer_size,
use_gru=use_gru,
share_rnn_weights=share_rnn_weights)
def _create_network(self, vocab_size, num_conv_layers, num_rnn_layers,
rnn_layer_size, use_gru, share_rnn_weights):
"""Create data layers and model network."""
# paddle.data_type.dense_array is used for variable batch input.
# The size 161 * 161 is only an placeholder value and the real shape
# of input batch data will be induced during training.
audio_data = paddle.layer.data(name="audio_spectrogram",
type=paddle.data_type.dense_array(161 *
161))
text_data = paddle.layer.data(
name="transcript_text",
type=paddle.data_type.integer_value_sequence(vocab_size))
seq_offset_data = paddle.layer.data(
name='sequence_offset',
type=paddle.data_type.integer_value_sequence(1))
seq_len_data = paddle.layer.data(
name='sequence_length',
type=paddle.data_type.integer_value_sequence(1))
index_range_datas = []
for i in xrange(num_rnn_layers):
index_range_datas.append(
paddle.layer.data(name='conv%d_index_range' % i,
type=paddle.data_type.dense_vector(6)))
self._log_probs, self._loss = deep_speech_v2_network(
audio_data=audio_data,
text_data=text_data,
seq_offset_data=seq_offset_data,
seq_len_data=seq_len_data,
index_range_datas=index_range_datas,
dict_size=vocab_size,
num_conv_layers=num_conv_layers,
num_rnn_layers=num_rnn_layers,
rnn_size=rnn_layer_size,
use_gru=use_gru,
share_rnn_weights=share_rnn_weights)
def create_network(self, is_infer=False):
"""Create data layers and model network.
:param is_training: Whether to create a network for training.
:type is_training: bool
:return reader: Reader for input.
:rtype reader: read generater
:return log_probs: An output unnormalized log probability layer.
:rtype lig_probs: Varable
:return loss: A ctc loss layer.
:rtype loss: Variable
"""
if not is_infer:
input_fields = {
'names': ['audio_data', 'text_data', 'seq_len_data', 'masks'],
'shapes': [[None, 161, None], [None, 1], [None, 1], [None, 32, 81, None]],
'dtypes': ['float32', 'int32', 'int64', 'float32'],
'lod_levels': [0, 1, 0, 0]
}
inputs = [
fluid.data(name=input_fields['names'][i],
shape=input_fields['shapes'][i],
dtype=input_fields['dtypes'][i],
lod_level=input_fields['lod_levels'][i])
for i in range(len(input_fields['names']))
]
reader = fluid.io.DataLoader.from_generator(feed_list=inputs,
capacity=128,
iterable=False,
use_double_buffer=True)
(audio_data, text_data, seq_len_data, masks) = inputs
else:
audio_data = fluid.data(name='audio_data',
shape=[None, 161, None],
dtype='float32',
lod_level=0)
seq_len_data = fluid.data(name='seq_len_data',
shape=[None, 1],
dtype='int64',
lod_level=0)
masks = fluid.data(name='masks',
shape=[None, 32, 81, None],
dtype='float32',
lod_level=0)
text_data = None
reader = fluid.DataFeeder([audio_data, seq_len_data, masks], self._place)
log_probs, loss = deep_speech_v2_network(audio_data=audio_data,
text_data=text_data,
seq_len_data=seq_len_data,
masks=masks,
dict_size=self._vocab_size,
num_conv_layers=self._num_conv_layers,
num_rnn_layers=self._num_rnn_layers,
rnn_size=self._rnn_layer_size,
use_gru=self._use_gru,
share_rnn_weights=self._share_rnn_weights)
return reader, log_probs, loss
