Merge pull request #517 from PaddlePaddle/1.8

update data source and remove useless code

data/aishell/aishell.py

@@ -19,6 +19,7 @@ from data_utils.utility import download, unpack
 DATA_HOME = os.path.expanduser('~/.cache/paddle/dataset/speech')
 
 URL_ROOT = 'http://www.openslr.org/resources/33'
+URL_ROOT = 'https://openslr.magicdatatech.com/resources/33'
 DATA_URL = URL_ROOT + '/data_aishell.tgz'
 MD5_DATA = '2f494334227864a8a8fec932999db9d8'
 

data/librispeech/librispeech.py

@@ -20,6 +20,7 @@ import io
 from data_utils.utility import download, unpack
 
 URL_ROOT = "http://www.openslr.org/resources/12"
+URL_ROOT = "https://openslr.magicdatatech.com/resources/12"
 URL_TEST_CLEAN = URL_ROOT + "/test-clean.tar.gz"
 URL_TEST_OTHER = URL_ROOT + "/test-other.tar.gz"
 URL_DEV_CLEAN = URL_ROOT + "/dev-clean.tar.gz"

data/voxforge/voxforge.py

@@ -11,6 +11,7 @@ from __future__ import print_function
 
 import os
 import codecs
+import datetime
 import soundfile
 import json
 import argparse

data_utils/data.py

@@ -276,8 +276,8 @@ class DataGenerator(object):
         def reader():
             for instance in manifest:
                 inst = self.process_utterance(instance["audio_filepath"],
-                                              instance["text"]),
-                yield inst[0]
+                                              instance["text"])
+                yield inst
 
         return reader
 

data_utils/speech.py

@@ -3,6 +3,7 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
+import numpy as np
 from data_utils.audio import AudioSegment