__init__.py 文件源码

def load_lre_list():
  """ The header include following column:
  * name: LDC2017E22/data/ara-acm/ar-20031215-034005_0-a.sph
  * lre: {'train17', 'eval15', 'train15', 'dev17', 'eval17'}
  * language: {'ara-arb', 'eng-sas', 'fre-hat', 'zho-wuu',
               'eng-gbr', 'ara-ary', 'eng-usg', 'spa-lac',
               'ara-apc', 'qsl-pol', 'spa-eur', 'fre-waf',
               'zho-cdo', 'qsl-rus', 'spa-car', 'ara-arz',
               'zho-cmn', 'por-brz', 'zho-yue', 'zho-nan',
               'ara-acm'}
  * corpus: {'pcm', 'alaw', 'babel', 'ulaw', 'vast', 'mls14'}
  * duration: {'3', '30', '5', '15', '10', '20', '1000', '25'}

  Note
  ----
  Suggested namming scheme:
    `lre/lang/corpus/dur/base_name`
  """
  link = b'aHR0cHM6Ly9zMy5hbWF6b25hd3MuY29tL2FpLWRhdGFzZXRzL2xyZV9saXN0LnR4dA==\n'
  link = str(base64.decodebytes(link), 'utf-8')
  path = get_file(fname=os.path.basename(link),
                  origin=link,
                  outdir=get_datasetpath(root='~'))
  return np.genfromtxt(fname=path, dtype=str, delimiter=' ',
                       skip_header=1)