def gen_dummy_meta(num_spk, num_utt_per_spk):
''' Generate a dummy data. '''
meta = kaldi_dir.KaldiMetaData()
for spk_idx in range(num_spk):
for utt_idx in range(num_utt_per_spk):
spk = str(spk_idx)
utt = '%s_%d' % (spk, utt_idx)
utt_meta = kaldi_dir.Utt()
utt_meta.feat = 'foo/bar/feat/%s' % (utt)
utt_meta.vad = 'foo/bar/vad/%s' % (utt)
utt_meta.spk = spk
meta.utts[utt] = utt_meta
meta.collect_spks_from_utts()
return meta
def gen_dummy_data_dir(data_dir,
num_spk,
num_utt_per_spk,
feat_len=100,
feat_dim=40):
''' Generate a dummy data directory and return its meta. '''
os.makedirs(data_dir, exist_ok=True)
meta = kaldi_dir.KaldiMetaData()
feats = {}
vads = {}
for spk_idx in range(num_spk):
for utt_idx in range(num_utt_per_spk):
spk = str(spk_idx)
utt = '%s_%d' % (spk, utt_idx)
utt_meta = kaldi_dir.Utt()
feat_mat = np.ones((feat_len, feat_dim), dtype='float32')
feats[utt] = feat_mat
utt_meta.featlen = feat_len
vad_mat = np.ones((feat_len, ), dtype='float32')
vads[utt] = vad_mat
utt_meta.spk = spk
meta.utts[utt] = utt_meta
meta.collect_spks_from_utts()
meta.dump(data_dir, True)
feats_ark_path = os.path.join(data_dir, 'feats.ark')
feats_scp_path = os.path.join(data_dir, 'feats.scp')
kaldiio.save_ark(feats_ark_path, feats, scp=feats_scp_path, text=True)
vad_ark_path = os.path.join(data_dir, 'vad.ark')
vad_scp_path = os.path.join(data_dir, 'vad.scp')
kaldiio.save_ark(vad_ark_path, vads, scp=vad_scp_path, text=True)
loaded_meta = kaldi_dir.KaldiMetaData()
loaded_meta.load(data_dir)
return loaded_meta
def test_dump_and_load(self):
''' test dump and load data '''
temp_dir = self.get_temp_dir()
num_spk = 5
num_utt_per_spk = 3
meta = gen_dummy_meta(num_spk, num_utt_per_spk)
meta.dump(temp_dir, True)
with open(os.path.join(temp_dir, 'feats.scp'), 'r') as fp_in:
logging.info('feats.scp:\n%s' % (fp_in.read()))
loaded_meta = kaldi_dir.KaldiMetaData()
loaded_meta.load(temp_dir)
self.assertEqual(len(meta.utts), len(loaded_meta.utts))
for utt_key in meta.utts.keys():
self.assertIn(utt_key, loaded_meta.utts)
self.assertEqual(len(meta.spks), len(loaded_meta.spks))
for spk_key in meta.spks.keys():
self.assertIn(spk_key, loaded_meta.spks)
def main():
''' The main function. '''
logging.set_verbosity(logging.INFO)
parser = argparse.ArgumentParser()
parser.add_argument('--num-spk-cv', type=float, default=0)
parser.add_argument('--num-utt-cv', type=float, default=0)
parser.add_argument('--cv-spk-percent', type=float, default=0.0)
parser.add_argument('--cv-utt-percent', type=float, default=0.0)
parser.add_argument('--fair-choice', type=bool, default=True)
parser.add_argument('data_dir')
parser.add_argument('data_dir_tr')
parser.add_argument('data_dir_cv')
args = parser.parse_args()
num_spk_cv = args.num_spk_cv
num_utt_cv = args.num_utt_cv
if args.cv_spk_percent > 0:
if args.cv_spk_percent >= 100:
raise ValueError('cv_spk_percent cannot >= 100')
num_spk_cv = args.cv_spk_percent / 100
if args.cv_utt_percent > 0:
if args.cv_utt_percent >= 100:
raise ValueError('cv_utt_percent cannot >= 100')
num_utt_cv = args.cv_utt_percent / 100
if num_spk_cv == 0 and num_utt_cv == 0:
num_spk_cv = 0.1
meta = kaldi_dir.KaldiMetaData()
meta.load(args.data_dir)
meta_tr, meta_cv = kaldi_dir_utils.subset_data_dir_tr_cv(
meta,
num_spk_cv=num_spk_cv,
num_utt_cv=num_utt_cv,
fair_choice=args.fair_choice)
logging.info('#spks tr: %d, cv: %d; #utts tr: %d, cv: %d' %
(len(meta_tr.spks), len(meta_cv.spks), len(
meta_tr.utts), len(meta_cv.utts)))
meta_tr.dump(args.data_dir_tr, overwrite=True)
meta_cv.dump(args.data_dir_cv, overwrite=True)