def use_fmllr(feat,fmllrMat,utt2spk,outFile=None):
'''
Transfrom to fmllr feature.
Share Args:
Null
Parallel Args:
<feat>: exkaldi feature or index table object.
<fmllrMat>: exkaldi fMLLR transform matrix or index table object.
<utt2spk>: file name or ListTable object.
<outFile>: output file name.
Return:
exkaldi feature or index table object.
'''
feats,fmllrMats,utt2spks,outFiles = check_multiple_resources(feat,fmllrMat,utt2spk,outFile=outFile)
names = []
for index,feat,fmllrMat,utt2spk in zip(range(len(outFiles)),feats,fmllrMats,utt2spks):
# verify data
declare.is_feature("feat",feat)
declare.is_fmllr_matrix("fmllrMat",fmllrMat)
# verify utt2spk
declare.is_potential_list_table("utt2spk",utt2spk)
names.append(f"fmllr({feat.name},{fmllrMat.name})")
cmdPattern = 'transform-feats --utt2spk=ark:{utt2spk} {transMat} {feat} ark:{outFile}'
resources = {"feat":feats,"transMat":fmllrMats,"utt2spk":utt2spks,"outFile":outFiles}
return run_kaldi_commands_parallel(resources,cmdPattern,analyzeResult=True,generateArchive="feat",archiveNames=names)
def compute_cmvn_stats(feat,spk2utt=None,name="cmvn",outFile=None):
'''
Compute CMVN statistics.
Share Args:
Null
Parrallel Args:
<feat>: exkaldi feature object or index table object.
<spk2utt>: spk2utt file or exkaldi ListTable object.
<name>: name of output CMVN object.
<outFile>: output file name.
Return:
exkaldi CMVN statistics or index table object.
'''
feats,spk2utts,names,outFiles = check_multiple_resources(feat,spk2utt,name,outFile=outFile)
for feat,spk2utt in zip(feats,spk2utts):
# verify feature
declare.is_feature("feat",feat)
# verify spk2utt
if spk2utt is not None:
declare.is_potential_list_table("spk2utt",spk2utt)
if spk2utts[0] is None:
cmdPattern = 'compute-cmvn-stats {feat} ark:{outFile}'
resources = {"feat":feats,"outFile":outFiles}
else:
cmdPattern = 'compute-cmvn-stats --spk2utt=ark:{spk2utt} {feat} ark:{outFile}'
resources = {"feat":feats,"spk2utt":spk2utts,"outFile":outFiles}
return run_kaldi_commands_parallel(resources,cmdPattern,analyzeResult=True,generateArchive="cmvn",archiveNames=names)
def utt_to_spk(utts,utt2spk):
'''
Accept a list of utterance IDs and return their corresponding speaker IDs.
Args:
<utts>: a string or list or tuple of utterance IDs.
<utt2spk>: utt2spk file or ListTable object.
Return:
a list of speaker IDs.
'''
declare.is_classes("utterance IDs",utts,(str,tuple,list))
if not isinstance(utts,str):
declare.members_are_valid_strings("utterance IDs",utts)
else:
utts = [utts,]
declare.is_potential_list_table("utt2spk",utt2spk)
if isinstance(utt2spk,str):
utt2spk = load_list_table(utt2spk)
spks = []
for utt in utts:
try:
spk = utt2spk[utt]
except KeyError:
raise WrongOperation(f"Miss utterance ID {utt} in utt2spk map.")
else:
declare.is_valid_string("The value of utt2spk",utt)
spktemp = spk.strip().split(maxsplit=1)
assert len(spktemp) == 1,f"speaker ID in utt2spk has unexpected space: {spk}."
spks.append(spktemp[0])
return sorted(list(set(spks)))
def spk_to_utt(spks,spk2utt):
'''
Accept a list of speaker IDs and return their corresponding utterance IDs.
Args:
<spks>: a string or list or tuple of speaker IDs.
<spk2utt>: spk2utt file or ListTable object.
Return:
a list of utterance IDs.
'''
declare.is_classes("speaker IDs",spks,(str,tuple,list))
if not isinstance(spks,str):
declare.members_are_valid_strings("speaker IDs",spks)
else:
spks = [spks,]
declare.is_potential_list_table("spk2utt",spk2utt)
if isinstance(spk2utt,str):
spk2utt = load_list_table(spk2utt)
utts = []
for spk in spks:
try:
utt = spk2utt[spk]
except KeyError:
raise WrongOperation(f"Miss speaker ID {spk} in spk2utt map.")
else:
declare.is_valid_string("The value of spk2utt",utt)
utts.extend(utt.strip().split())
return sorted(list(set(utts)))
def utt2spk_to_spk2utt(utt2spk,outFile=None):
'''
Transform utt2spk to spk2utt.
Args:
<utt2spk>: file name or exkaldi ListTable object.
<outFile>: file name or None.
Return:
file name or exakldi ListTable object.
'''
declare.is_potential_list_table("utt2spk",utt2spk)
if outFile is not None:
declare.is_valid_file_name(outFile)
if isinstance(utt2spk,str):
utt2spk = load_list_table(utt2spk)
spk2utt = ListTable(name="spk2utt")
for utt,spk in utt2spk.items():
declare.is_valid_string("utterance ID",utt)
declare.is_valid_string("speaker ID",spk)
assert utt.count(" ") == 0,f"<utterance ID> is not a continuous string but spaces existed: {utt}."
assert spk.count(" ") == 0,f"<speaker ID> is not a continuous string but spaces existed: {spk}."
try:
spk2utt[spk] += f" {utt}"
except KeyError:
spk2utt[spk] = utt
if outFile is None:
return spk2utt
else:
spk2utt.save(outFile)
return outFile
def use_cmvn(feat,cmvn,utt2spk=None,std=False,outFile=None):
'''
Apply CMVN statistics to feature.
Share Args:
Null
Parrallel Args:
<feat>: exkaldi feature or index table object.
<cmvn>: exkaldi CMVN statistics or index object.
<utt2spk>: file path or ListTable object.
<std>: If true,apply std normalization.
<outFile>: out file name.
Return:
feature or index table object.
'''
feats,cmvns,utt2spks,stds,outFiles = check_multiple_resources(feat,cmvn,utt2spk,std,outFile=outFile)
names = []
for i,feat,cmvn,utt2spk,std in zip(range(len(outFiles)),feats,cmvns,utt2spks,stds):
# verify feature and cmvn
declare.is_feature("feat",feat)
declare.is_cmvn("cmvn",cmvn)
# verify utt2spk
if utt2spk is not None:
declare.is_potential_list_table("utt2spk",utt2spk)
# std
declare.is_bool("std",std)
#stds[i] = "true" if std else "false"
names.append( f"cmvn({feat.name},{cmvn.name})" )
if utt2spks[0] is None:
cmdPattern = 'apply-cmvn --norm-vars={std} {cmvn} {feat} ark:{outFile}'
resources = {"feat":feats,"cmvn":cmvns,"std":stds,"outFile":outFiles}
else:
cmdPattern = 'apply-cmvn --norm-vars={std} --utt2spk=ark:{utt2spk} {cmvn} {feat} ark:{outFile}'
resources = {"feat":feats,"cmvn":cmvns,"utt2spk":utt2spks,"std":stds,"outFile":outFiles}
return run_kaldi_commands_parallel(resources,cmdPattern,analyzeResult=True,generateArchive="feat",archiveNames=names)
def spk2utt_to_utt2spk(spk2utt,outFile=None):
'''
Transform spk2utt file to utt2spk file.
Args:
<spk2utt>: file name or exkaldi ListTable object.
<outFile>: file name or None.
Return:
file name or exakldi ListTable object.
'''
declare.is_potential_list_table("spk2utt",spk2utt)
if outFile is not None:
declare.is_valid_file_name(outFile)
if isinstance(spk2utt,str):
spk2utt = load_list_table(spk2utt)
utt2spk = ListTable(name="utt2spk")
for spk,utts in spk2utt.items():
declare.is_valid_string("utterance IDs",utts)
declare.is_valid_string("speaker ID",spk)
assert spk.count(" ") == 0,f"<speaker ID> is not a continuous string but spaces existed: {spk}."
for utt in utts.split():
try:
utt2spk[utt]
except KeyError:
utt2spk[utt] = spk
else:
raise WrongDataFormat(f"utterance ID:{utt} has existed toward multiple speakers.")
if outFile is None:
return utt2spk
else:
utt2spk.save(outFile)
return outFile
