Sort importer imports with isort

.isort.cfg

@@ -0,0 +1,4 @@
+[settings]
+line_length=80
+multi_line_output=3
+default_section=FIRSTPARTY

bin/build_sdb.py

@@ -6,11 +6,19 @@ Use "python3 build_sdb.py -h" for help
 from __future__ import absolute_import, division, print_function
 
 import argparse
+
 import progressbar
 
+from deepspeech_training.util.audio import (
+    AUDIO_TYPE_OPUS,
+    AUDIO_TYPE_WAV,
+    change_audio_types
+)
 from deepspeech_training.util.downloader import SIMPLE_BAR
-from deepspeech_training.util.audio import change_audio_types, AUDIO_TYPE_WAV, AUDIO_TYPE_OPUS
+from deepspeech_training.util.sample_collections import (
-from deepspeech_training.util.sample_collections import samples_from_files, DirectSDBWriter
+    DirectSDBWriter,
+    samples_from_files
+)
 
 AUDIO_TYPE_LOOKUP = {
     'wav': AUDIO_TYPE_WAV,

bin/graphdef_binary_to_text.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-import tensorflow.compat.v1 as tfv1
 import sys
 
+import tensorflow.compat.v1 as tfv1
 from google.protobuf import text_format
 
 

bin/import_aidatatang.py

@@ -3,9 +3,10 @@ from __future__ import absolute_import, division, print_function
 
 import glob
 import os
-import pandas
 import tarfile
 
+import pandas
+
 from deepspeech_training.util.importers import get_importers_parser
 
 COLUMN_NAMES = ['wav_filename', 'wav_filesize', 'transcript']

bin/import_aishell.py

@@ -3,9 +3,10 @@ from __future__ import absolute_import, division, print_function
 
 import glob
 import os
-import pandas
 import tarfile
 
+import pandas
+
 from deepspeech_training.util.importers import get_importers_parser
 
 COLUMNNAMES = ['wav_filename', 'wav_filesize', 'transcript']

bin/import_cv.py

@@ -3,15 +3,22 @@ from __future__ import absolute_import, division, print_function
 
 import csv
 import os
-import progressbar
-import sox
 import subprocess
 import tarfile
-
 from glob import glob
 from multiprocessing import Pool
-from deepspeech_training.util.importers import validate_label_eng as validate_label, get_counter, get_imported_samples, print_import_report
+
-from deepspeech_training.util.downloader import maybe_download, SIMPLE_BAR
+import progressbar
+import sox
+
+from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
+from deepspeech_training.util.importers import (
+    get_counter,
+    get_imported_samples,
+    print_import_report
+)
+from deepspeech_training.util.importers import \
+    validate_label_eng as validate_label
 
 FIELDNAMES = ['wav_filename', 'wav_filesize', 'transcript']
 SAMPLE_RATE = 16000

bin/import_cv2.py

@@ -10,16 +10,22 @@ from __future__ import absolute_import, division, print_function
 
 import csv
 import os
-import progressbar
-import sox
 import subprocess
 import unicodedata
-
 from multiprocessing import Pool
-from deepspeech_training.util.downloader import SIMPLE_BAR
-from deepspeech_training.util.text import Alphabet
-from deepspeech_training.util.importers import get_importers_parser, get_validate_label, get_counter, get_imported_samples, print_import_report
 
+import progressbar
+import sox
+
+from deepspeech_training.util.downloader import SIMPLE_BAR
+from deepspeech_training.util.importers import (
+    get_counter,
+    get_imported_samples,
+    get_importers_parser,
+    get_validate_label,
+    print_import_report
+)
+from deepspeech_training.util.text import Alphabet
 
 FIELDNAMES = ['wav_filename', 'wav_filesize', 'transcript']
 SAMPLE_RATE = 16000

bin/import_fisher.py

@@ -1,20 +1,24 @@
 #!/usr/bin/env python
 from __future__ import absolute_import, division, print_function
 
-# Prerequisite: Having the sph2pipe tool in your PATH:
-# https://www.ldc.upenn.edu/language-resources/tools/sphere-conversion-tools
-
 import codecs
 import fnmatch
-import librosa
 import os
-import pandas
-import soundfile # <= Has an external dependency on libsndfile
 import subprocess
 import sys
 import unicodedata
 
-from deepspeech_training.util.importers import validate_label_eng as validate_label
+import librosa
+import pandas
+import soundfile  # <= Has an external dependency on libsndfile
+
+from deepspeech_training.util.importers import \
+    validate_label_eng as validate_label
+
+# Prerequisite: Having the sph2pipe tool in your PATH:
+# https://www.ldc.upenn.edu/language-resources/tools/sphere-conversion-tools
+
+
 
 def _download_and_preprocess_data(data_dir):
     # Assume data_dir contains extracted LDC2004S13, LDC2004T19, LDC2005S13, LDC2005T19

bin/import_freestmandarin.py

@@ -2,11 +2,12 @@
 from __future__ import absolute_import, division, print_function
 
 import glob
-import numpy as np
 import os
-import pandas
 import tarfile
 
+import numpy as np
+import pandas
+
 from deepspeech_training.util.importers import get_importers_parser
 
 COLUMN_NAMES = ['wav_filename', 'wav_filesize', 'transcript']

bin/import_gram_vaani.py

@@ -4,15 +4,18 @@ import csv
 import logging
 import math
 import os
-import pandas as pd
-import swifter
 import subprocess
 import urllib
-
-from deepspeech_training.util.importers import get_importers_parser, get_validate_label
 from pathlib import Path
+
+import pandas as pd
 from sox import Transformer
 
+import swifter
+from deepspeech_training.util.importers import (
+    get_importers_parser,
+    get_validate_label
+)
 
 __version__ = "0.1.0"
 _logger = logging.getLogger(__name__)

bin/import_ldc93s1.py

@@ -1,12 +1,14 @@
 #!/usr/bin/env python
 from __future__ import absolute_import, division, print_function
 
-import pandas
 import os
 import sys
 
+import pandas
+
 from deepspeech_training.util.downloader import maybe_download
 
+
 def _download_and_preprocess_data(data_dir):
     # Conditionally download data
     LDC93S1_BASE = "LDC93S1"

bin/import_librivox.py

@@ -4,17 +4,18 @@ from __future__ import absolute_import, division, print_function
 import codecs
 import fnmatch
 import os
-import pandas
-import progressbar
 import subprocess
 import sys
 import tarfile
 import unicodedata
 
-from deepspeech_training.util.downloader import maybe_download
+import pandas
+import progressbar
 from sox import Transformer
 from tensorflow.python.platform import gfile
 
+from deepspeech_training.util.downloader import maybe_download
+
 SAMPLE_RATE = 16000
 
 def _download_and_preprocess_data(data_dir):

bin/import_lingua_libre.py

@@ -4,20 +4,25 @@ from __future__ import absolute_import, division, print_function
 import argparse
 import csv
 import os
-import progressbar
 import re
-import sox
 import subprocess
 import unicodedata
 import zipfile
-
-from deepspeech_training.util.downloader import maybe_download
-from deepspeech_training.util.downloader import SIMPLE_BAR
-from deepspeech_training.util.importers import get_importers_parser, get_validate_label, get_counter, get_imported_samples, print_import_report
-from deepspeech_training.util.text import Alphabet
 from glob import glob
 from multiprocessing import Pool
 
+import progressbar
+import sox
+
+from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
+from deepspeech_training.util.importers import (
+    get_counter,
+    get_imported_samples,
+    get_importers_parser,
+    get_validate_label,
+    print_import_report
+)
+from deepspeech_training.util.text import Alphabet
 
 FIELDNAMES = ['wav_filename', 'wav_filesize', 'transcript']
 SAMPLE_RATE = 16000

bin/import_m-ailabs.py

@@ -4,18 +4,24 @@ from __future__ import absolute_import, division, print_function
 
 import csv
 import os
-import progressbar
 import subprocess
 import tarfile
 import unicodedata
-
-from deepspeech_training.util.downloader import maybe_download
-from deepspeech_training.util.downloader import SIMPLE_BAR
-from deepspeech_training.util.importers import get_importers_parser, get_validate_label, get_counter, get_imported_samples, print_import_report
-from deepspeech_training.util.text import Alphabet
 from glob import glob
 from multiprocessing import Pool
 
+import progressbar
+
+from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
+from deepspeech_training.util.importers import (
+    get_counter,
+    get_imported_samples,
+    get_importers_parser,
+    get_validate_label,
+    print_import_report
+)
+from deepspeech_training.util.text import Alphabet
+
 FIELDNAMES = ['wav_filename', 'wav_filesize', 'transcript']
 SAMPLE_RATE = 16000
 MAX_SECS = 15

bin/import_magicdata.py

@@ -3,10 +3,11 @@ from __future__ import absolute_import, division, print_function
 
 import glob
 import os
-import pandas
 import tarfile
 import wave
 
+import pandas
+
 from deepspeech_training.util.importers import get_importers_parser
 
 COLUMN_NAMES = ['wav_filename', 'wav_filesize', 'transcript']

bin/import_primewords.py

@@ -3,11 +3,12 @@ from __future__ import absolute_import, division, print_function
 
 import glob
 import json
-import numpy as np
 import os
-import pandas
 import tarfile
 
+import numpy as np
+import pandas
+
 from deepspeech_training.util.importers import get_importers_parser
 
 COLUMN_NAMES = ['wav_filename', 'wav_filesize', 'transcript']

bin/import_slr57.py

@@ -3,20 +3,26 @@ from __future__ import absolute_import, division, print_function
 
 import csv
 import os
-import progressbar
 import re
-import sox
 import subprocess
 import tarfile
 import unicodedata
 import zipfile
-
-from deepspeech_training.util.downloader import maybe_download, SIMPLE_BAR
-from deepspeech_training.util.importers import get_importers_parser, get_validate_label, get_counter, get_imported_samples, print_import_report
-from deepspeech_training.util.text import Alphabet
 from glob import glob
 from multiprocessing import Pool
 
+import progressbar
+import sox
+
+from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
+from deepspeech_training.util.importers import (
+    get_counter,
+    get_imported_samples,
+    get_importers_parser,
+    get_validate_label,
+    print_import_report
+)
+from deepspeech_training.util.text import Alphabet
 
 FIELDNAMES = ['wav_filename', 'wav_filesize', 'transcript']
 SAMPLE_RATE = 16000

bin/import_swb.py

@@ -6,19 +6,20 @@ from __future__ import absolute_import, division, print_function
 # from the deepspeech directory run with: ./bin/import_swb.py ./data/swb/
 import codecs
 import fnmatch
-import librosa
 import os
-import pandas
-import requests
-import soundfile # <= Has an external dependency on libsndfile
 import subprocess
 import sys
 import tarfile
 import unicodedata
 import wave
 
-from deepspeech_training.util.importers import validate_label_eng as validate_label
+import librosa
+import pandas
+import requests
+import soundfile  # <= Has an external dependency on libsndfile
 
+from deepspeech_training.util.importers import \
+    validate_label_eng as validate_label
 
 # ARCHIVE_NAME refers to ISIP alignments from 01/29/03
 ARCHIVE_NAME = 'switchboard_word_alignments.tar.gz'

bin/import_swc.py

@@ -8,23 +8,25 @@ from __future__ import absolute_import, division, print_function
 import argparse
 import csv
 import os
-import progressbar
 import random
 import re
 import shutil
-import sox
 import sys
 import tarfile
 import unicodedata
 import wave
 import xml.etree.cElementTree as ET
-
-from glob import glob
 from collections import Counter
+from glob import glob
 from multiprocessing.pool import ThreadPool
+
+import progressbar
+import sox
+
+from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
+from deepspeech_training.util.importers import \
+    validate_label_eng as validate_label
 from deepspeech_training.util.text import Alphabet
-from deepspeech_training.util.importers import validate_label_eng as validate_label
-from deepspeech_training.util.downloader import maybe_download, SIMPLE_BAR
 
 SWC_URL = "https://www2.informatik.uni-hamburg.de/nats/pub/SWC/SWC_{language}.tar"
 SWC_ARCHIVE = "SWC_{language}.tar"

bin/import_ted.py

@@ -1,17 +1,18 @@
 #!/usr/bin/env python
 from __future__ import absolute_import, division, print_function
 
-import pandas
 import sys
 import tarfile
 import unicodedata
 import wave
-
 from glob import glob
 from os import makedirs, path, remove, rmdir
+
+import pandas
 from sox import Transformer
-from deepspeech_training.util.downloader import maybe_download
 from tensorflow.python.platform import gfile
+
+from deepspeech_training.util.downloader import maybe_download
 from deepspeech_training.util.stm import parse_stm_file
 
 

bin/import_timit.py

@@ -11,13 +11,15 @@
 '''
 
 import errno
+import fnmatch
 import os
-from os import path
+import subprocess
 import sys
 import tarfile
-import fnmatch
+from os import path
+
 import pandas as pd
-import subprocess
+
 
 def clean(word):
     # LC ALL & strip punctuation which are not required

bin/import_ts.py

@@ -3,18 +3,23 @@ from __future__ import absolute_import, division, print_function
 
 import csv
 import os
-import progressbar
 import re
-import sox
 import subprocess
-import unidecode
 import zipfile
-
-from deepspeech_training.util.downloader import maybe_download
-from deepspeech_training.util.downloader import SIMPLE_BAR
-from deepspeech_training.util.importers import get_importers_parser, get_validate_label, get_counter, get_imported_samples, print_import_report
 from multiprocessing import Pool
 
+import progressbar
+import sox
+
+import unidecode
+from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
+from deepspeech_training.util.importers import (
+    get_counter,
+    get_imported_samples,
+    get_importers_parser,
+    get_validate_label,
+    print_import_report
+)
 
 FIELDNAMES = ['wav_filename', 'wav_filesize', 'transcript']
 SAMPLE_RATE = 16000

bin/import_tuda.py

@@ -8,15 +8,17 @@ from __future__ import absolute_import, division, print_function
 import argparse
 import csv
 import os
-import progressbar
 import tarfile
 import unicodedata
 import wave
 import xml.etree.cElementTree as ET
-
 from collections import Counter
-from deepspeech_training.util.downloader import maybe_download, SIMPLE_BAR
+
-from deepspeech_training.util.importers import validate_label_eng as validate_label
+import progressbar
+
+from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
+from deepspeech_training.util.importers import \
+    validate_label_eng as validate_label
 from deepspeech_training.util.text import Alphabet
 
 TUDA_VERSION = 'v2'

bin/import_vctk.py

@@ -4,17 +4,21 @@
 # as per https://homepages.inf.ed.ac.uk/jyamagis/page3/page58/page58.html
 from __future__ import absolute_import, division, print_function
 
-import librosa
 import os
-import progressbar
 import random
 import re
-
-from deepspeech_training.util.downloader import maybe_download, SIMPLE_BAR
-from deepspeech_training.util.importers import get_counter, get_imported_samples, print_import_report
 from multiprocessing import Pool
 from zipfile import ZipFile
 
+import librosa
+import progressbar
+
+from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
+from deepspeech_training.util.importers import (
+    get_counter,
+    get_imported_samples,
+    print_import_report
+)
 
 SAMPLE_RATE = 16000
 MAX_SECS = 10

bin/import_voxforge.py

@@ -3,20 +3,21 @@ from __future__ import absolute_import, division, print_function
 
 import codecs
 import os
-import pandas
 import re
 import tarfile
 import threading
 import unicodedata
-
-from bs4 import BeautifulSoup
-from deepspeech_training.util.downloader import maybe_download
 from glob import glob
 from multiprocessing.pool import ThreadPool
 from os import makedirs, path
+
+import pandas
+from bs4 import BeautifulSoup
 from six.moves import urllib
 from tensorflow.python.platform import gfile
 
+from deepspeech_training.util.downloader import maybe_download
+
 """The number of jobs to run in parallel"""
 NUM_PARALLEL = 8
 
@@ -188,7 +189,3 @@ def _generate_dataset(data_dir, data_set):
 
 if __name__=="__main__":
     _download_and_preprocess_data(sys.argv[1])
-
-
-
-

bin/ops_in_graph.py

@@ -1,9 +1,11 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-import tensorflow.compat.v1 as tfv1
 import sys
 
+import tensorflow.compat.v1 as tfv1
+
+
 def main():
     with tfv1.gfile.FastGFile(sys.argv[1], 'rb') as fin:
         graph_def = tfv1.GraphDef()

bin/play.py

@@ -10,7 +10,10 @@ import random
 import sys
 
 from deepspeech_training.util.audio import AUDIO_TYPE_PCM
-from deepspeech_training.util.sample_collections import samples_from_file, LabeledSample
+from deepspeech_training.util.sample_collections import (
+    LabeledSample,
+    samples_from_file
+)
 
 
 def play_sample(samples, index):