def read_rttm(cls, filename, normalize_cluster=False, encoding="utf8"):
"""
Read rttm file
:param filename: str input filename
:param normalize_cluster: normalize the cluster by removing upper case and accents
:return: a diarization object
"""
fic = open(filename, 'r', encoding=encoding)
diarization = Diar()
if not diarization._attributes.exist('gender'):
diarization.add_attribut(new_attribut='gender', default='U')
try:
for line in fic:
line = re.sub(r'\s+', ' ', line)
line = line.strip()
if line.startswith('#') or line.startswith(';;'):
continue
# split line into fields
spk, show, tmp0, start_str, length, tmp1, tmp2, cluster, tmp3 = line.split()
if spk == "SPEAKER":
start = int(round(float(start_str) * 100, 0))
stop = start + int(round(float(length) * 100, 0))
if normalize_cluster:
cluster = str2str_normalize(cluster)
diarization.append(show=show, cluster=cluster, start=start, stop=stop)
except Exception as e:
logging.error(sys.exc_info()[0])
logging.error(line)
fic.close()
return diarization
def read_mdtm(cls, filename, normalize_cluster=False, encoding="utf8"):
"""
Read a MDTM file
:param filename: the str input filename
:param normalize_cluster: normalize the cluster by removing upper case
and accents
:return: a diarization object
"""
fic = open(filename, 'r', encoding=encoding)
diarization = Diar()
if not diarization._attributes.exist('gender'):
diarization.add_attribut(new_attribut='gender', default='U')
for line in fic:
line = line.strip()
line = re.sub(r'\s+', ' ', line)
logging.debug(line)
if line.startswith('#') or line.startswith(';;'):
continue
# split line into fields
show, tmp, start_str, length, t, score, gender, cluster = line.split()
start = int(round(float(start_str) * 100, 0))
stop = start + int(round(float(length) * 100, 0))
if normalize_cluster:
cluster = str2str_normalize(cluster)
# print(show, tmp, start, length, gender, channel, env, speaker)
diarization.append(show=show, cluster=cluster, start=start, stop=stop, gender=gender)
fic.close()
return diarization
def read_ctm(cls, filename, normalize_cluster=False, encoding="utf8"):
"""
Read a segmentation file
:param filename: the str input filename
:param normalize_cluster: normalize the cluster by removing upper case
and accents
:return: a diarization object
"""
fic = open(filename, 'r', encoding=encoding)
diarization = Diar()
try:
for line in fic:
line = re.sub(r'\s+', ' ', line)
line = line.strip()
# logging.debug(line)
if line.startswith('#') or line.startswith(';;'):
continue
# split line into fields
show, tmp, start, length, word = line.split()
if normalize_cluster:
word = str2str_normalize(word)
# print(show, tmp, start, length, gender, channel, env, speaker)
diarization.append(show=show, cluster=word, start=int(start), stop=int(length) + int(start))
except Exception as e:
logging.error(sys.exc_info()[0])
# logging.error(line)
fic.close()
return diarization
def read_seg(cls, filename, normalize_cluster=False, encoding="utf8"):
"""
Read a segmentation file
:param filename: the str input filename
:param normalize_cluster: normalize the cluster speaker by removing upper
case and accents
:return: a diarization object
"""
fic = open(filename, 'r', encoding=encoding)
diarization = Diar()
if not diarization._attributes.exist('gender'):
diarization.add_attribut(new_attribut='gender', default='U')
if not diarization._attributes.exist('env'):
diarization.add_attribut(new_attribut='env', default='U')
if not diarization._attributes.exist('channel'):
diarization.add_attribut(new_attribut='channel', default='U')
try:
for line in fic:
line = re.sub(r'\s+', ' ', line)
line = line.strip()
# logging.debug(line)
if line.startswith('#') or line.startswith(';;'):
continue
# split line into fields
show, tmp, start, length, gender, channel, environment, name = line.split()
if normalize_cluster:
name = str2str_normalize(name)
# print(show, tmp, start, length, gender, channel, env, speaker)
diarization.append(show=show, cluster=name, start=int(start), stop=int(length) + int(start), env=environment, channel=channel, gender=gender)
except Exception as e:
logging.error(sys.exc_info()[0])
# logging.error(line)
fic.close()
return diarization
def read_stm(cls, filename, normalize_cluster=False, encoding="ISO-8859-1"):
"""
Read a segmentation file
:param filename: the str input filename
:param normalize_cluster: normalize the cluster by removing upper case
and accents
:return: a diarization object
"""
fic = open(filename, 'r', encoding=encoding)
diarization = Diar()
if not diarization._attributes.exist('gender'):
diarization.add_attribut(new_attribut='gender', default='U')
try:
for line in fic:
line = re.sub(r'\s+', ' ', line)
line = line.strip()
# logging.debug(line)
if line.startswith('#') or line.startswith(';;'):
continue
# split line into fields
split = line.split()
show = split[0]
loc = split[2]
if normalize_cluster:
loc = str2str_normalize(loc)
start = int(float(split[3]) * 100)
stop = int(float(split[4]) * 100)
addon = split[5].replace(">", "").replace("<", "").replace(",", " ")
lineBis = re.sub(r'\s+', ' ', addon)
lineBis = lineBis.strip()
gender = lineBis.split()[2]
if normalize_cluster:
word = str2str_normalize(word)
# print(show, tmp, start, length, gender, channel, env, speaker)
if gender == "female":
diarization.append(show=show, cluster=loc, start=start, stop=stop, gender="F")
elif gender == "male":
diarization.append(show=show, cluster=loc, start=start, stop=stop, gender="M")
else:
diarization.append(show=show, cluster=loc, start=start, stop=stop)
except Exception as e:
logging.error(sys.exc_info()[0])
logging.error(line)
fic.close()
return diarization