from pyannote.parser import MagicParser
import numpy
from itertools import tee, islice, chain, izip
if __name__ == '__main__':
#parser_spk = MagicParser().read('../reference/test2.repere')
parser_spk = MagicParser().read('../reference/test2.1.0.v2.repere')
parser_spo = MagicParser().read('../reference/test2.spoken.repere')
fout_spkshow = open(
'../spkshow/data/descripteur_prediction/test2.spkshow.spoken', 'w')
fout_spkseg = open(
'../spkseg/data/descripteur_prediction/test2.spkseg.spoken', 'w')
for show in parser_spo.uris:
spo = parser_spo(uri=show, modality="spoken")
spk = parser_spk(uri=show, modality="speaker")
list_spk = {}
l_st_previous_next = {}
for segment, track, label in spk.itertracks(label=True):
if type(
label
).__name__ != 'Unknown' and 'BFMTV_' not in label and 'LCP_' not in label:
list_spk.setdefault(show + '#' + label, {
'speech': [],
'spo': []
})
list_spk[show + '#' + label]['speech'].append(segment)
from pyannote.parser import MagicParser
import numpy
if __name__ == '__main__':
#parser_spk = MagicParser().read('../reference/test2.repere')
parser_spk = MagicParser().read('../reference/test2.1.0.v2.repere')
parser_ocr = MagicParser().read('../reference/test2.OCR.repere')
parser_uem = MagicParser().read('../reference/test2.uem')
#fout_spkshow = open('../spkshow/data/descripteur_prediction/test2.spkshow.OCR', 'w')
fout_spkseg = open('../spkseg/data/descripteur_prediction/test2.spkseg.OCR', 'w')
for show in parser_ocr.uris:
ocr = parser_ocr(uri=show, modality="written")
spk = parser_spk(uri=show, modality="speaker")
uem = parser_uem(uri=show)
list_spk = {}
for segment, track, label in spk.itertracks(label=True):
if type(label).__name__ != 'Unknown' and 'BFMTV_' not in label and 'LCP_' not in label :
list_spk.setdefault(show+'#'+label, {'speech':[], 'ocr':[], 'dur':[]})
list_spk[show+'#'+label]['speech'].append(segment)
list_spk[show+'#'+label]['dur'].append(segment.duration)
for segment, track, label in ocr.itertracks(label=True):
if show+'#'+label in list_spk:
list_spk[show+'#'+label]['ocr'].append(segment)
for spk in sorted(list_spk):
#spkshow
from pyannote.parser import MagicParser
if __name__ == '__main__':
parser = MagicParser().read('../reference/test2.repere')
fout_spkseg = open('../reference/list_spkseg', 'w')
fout_spkshow = open('../reference/list_spkshow', 'w')
list_spkshow = set([])
for show in parser.uris:
annotation = parser(uri=show, modality="speaker")
for segment, track, label in annotation.itertracks(label=True):
if type(
label
).__name__ != 'Unknown' and 'BFMTV_' not in label and 'LCP_' not in label:
fout_spkseg.write(show + " " + str(segment.start) + " " +
str(segment.end) + " " + label + '\n')
list_spkshow.add(show + '#' + label)
for spk in sorted(list_spkshow):
fout_spkshow.write(spk + '\n')
filter_funcs = [
lambdify([speech], sympify(expression))
for expression in filters]
filter_func = lambda speech: \
any(~func(speech) for func in filter_funcs)
else:
filter_func = None
spotting(protocol, subset, latencies, hypotheses, output_prefix,
filter_func=filter_func)
sys.exit(0)
# hypothesis
hypothesis_mdtm = arguments['<hypothesis.mdtm>']
hypotheses = MagicParser().read(hypothesis_mdtm, modality='speaker')
if arguments['detection']:
detection(protocol, subset, hypotheses,
collar=collar, skip_overlap=skip_overlap)
if arguments['segmentation']:
segmentation(protocol, subset, hypotheses, tolerance=tolerance)
if arguments['diarization']:
greedy = arguments['--greedy']
diarization(protocol, subset, hypotheses, greedy=greedy,
collar=collar, skip_overlap=skip_overlap)
if arguments['identification']:
identification(protocol, subset, hypotheses,
