提交 c8530dbb 编写于 作者: X Xinghai Sun

Merge branch 'develop' into network_structure

TRAIN_MANIFEST="cloud/cloud.manifest.train"
DEV_MANIFEST="cloud/cloud.manifest.dev"
CLOUD_MODEL_DIR="/pfs/dlnel/home/USERNAME/deepspeech2/model"
CLOUD_MODEL_DIR="./checkpoints"
BATCH_SIZE=256
NUM_GPU=8
NUM_NODE=1
......@@ -11,7 +11,7 @@ DS2_PATH=${PWD%/*}
cp -f pcloud_train.sh ${DS2_PATH}
paddlecloud submit \
-image bootstrapper:5000/wanghaoshuang/pcloud_ds2:latest \
-image bootstrapper:5000/paddlepaddle/pcloud_ds2:latest \
-jobname ${JOB_NAME} \
-cpu ${NUM_GPU} \
-gpu ${NUM_GPU} \
......
......@@ -85,9 +85,9 @@ class DataGenerator(object):
self._rng = random.Random(random_seed)
self._epoch = 0
# for caching tar files info
self.local_data = local()
self.local_data.tar2info = {}
self.local_data.tar2object = {}
self._local_data = local()
self._local_data.tar2info = {}
self._local_data.tar2object = {}
def process_utterance(self, filename, transcript):
"""Load, augment, featurize and normalize for speech data.
......@@ -240,16 +240,16 @@ class DataGenerator(object):
"""
if file.startswith('tar:'):
tarpath, filename = file.split(':', 1)[1].split('#', 1)
if 'tar2info' not in self.local_data.__dict__:
self.local_data.tar2info = {}
if 'tar2object' not in self.local_data.__dict__:
self.local_data.tar2object = {}
if tarpath not in self.local_data.tar2info:
if 'tar2info' not in self._local_data.__dict__:
self._local_data.tar2info = {}
if 'tar2object' not in self._local_data.__dict__:
self._local_data.tar2object = {}
if tarpath not in self._local_data.tar2info:
object, infoes = self._parse_tar(tarpath)
self.local_data.tar2info[tarpath] = infoes
self.local_data.tar2object[tarpath] = object
return self.local_data.tar2object[tarpath].extractfile(
self.local_data.tar2info[tarpath][filename])
self._local_data.tar2info[tarpath] = infoes
self._local_data.tar2object[tarpath] = object
return self._local_data.tar2object[tarpath].extractfile(
self._local_data.tar2info[tarpath][filename])
else:
return open(file, 'r')
......
......@@ -57,7 +57,7 @@ class AudioFeaturizer(object):
def featurize(self,
audio_segment,
allow_downsampling=True,
allow_upsamplling=True):
allow_upsampling=True):
"""Extract audio features from AudioSegment or SpeechSegment.
:param audio_segment: Audio/speech segment to extract features from.
......
......@@ -55,16 +55,20 @@ def bidirectional_simple_rnn_bn_layer(name, input, size, act):
:rtype: LayerOutput
"""
# input-hidden weights shared across bi-direcitonal rnn.
input_proj = paddle.layer.fc(
input_proj_forward = paddle.layer.fc(
input=input, size=size, act=paddle.activation.Linear(), bias_attr=False)
input_proj_backward = paddle.layer.fc(
input=input, size=size, act=paddle.activation.Linear(), bias_attr=False)
# batch norm is only performed on input-state projection
input_proj_bn = paddle.layer.batch_norm(
input=input_proj, act=paddle.activation.Linear())
input_proj_bn_forward = paddle.layer.batch_norm(
input=input_proj_forward, act=paddle.activation.Linear())
input_proj_bn_backward = paddle.layer.batch_norm(
input=input_proj_backward, act=paddle.activation.Linear())
# forward and backward in time
forward_simple_rnn = paddle.layer.recurrent(
input=input_proj_bn, act=act, reverse=False)
input=input_proj_bn_forward, act=act, reverse=False)
backward_simple_rnn = paddle.layer.recurrent(
input=input_proj_bn, act=act, reverse=True)
input=input_proj_bn_backward, act=act, reverse=True)
return paddle.layer.concat(input=[forward_simple_rnn, backward_simple_rnn])
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册