def load_list_table(target, name="listTable"):
'''
Generate a list table object from dict object or file.
Args:
<target>: dict object or a file path.
Return:
a ListTable object.
'''
declare.is_classes("target", target, [dict, ListTable, str])
newTable = ListTable(name=name)
if type_name(target) in ["dict", "ListTable"]:
newTable.update(target)
return newTable
else:
files = list_files(target)
for filePath in files:
with open(filePath, "r", encoding="utf-8") as fr:
lines = fr.readlines()
for index, line in enumerate(lines, start=1):
t = line.strip().split(maxsplit=1)
if len(t) < 2:
raise WrongDataFormat(
f"Line Number: {index}\n" + f"Line Content: {line}\n" +
f"Missing paired key and value information in file:{filePath}."
)
else:
newTable[t[0]] = t[1]
return newTable
def load_lat(target, name="lat"):
'''
Load lattice data.
Args:
<target>: bytes object, file path or exkaldi lattice object.
<hmm>: file path or exkaldi HMM object.
<wordSymbol>: file path or exkaldi LexiconBank object.
<name>: a string.
Return:
A exkaldi lattice object.
'''
if isinstance(target, bytes):
return Lattice(target, name)
elif isinstance(target, str):
target = list_files(target)
allData = []
for fileName in target:
if fileName.endswith('.gz'):
cmd = 'gunzip -c {}'.format(fileName)
out, err, _ = run_shell_command(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
if out == b'':
print(err.decode())
raise WrongDataFormat('Failed to load Lattice.')
else:
allData.append(out)
else:
try:
with open(fileName, 'rb') as fr:
out = fr.read()
except Exception as e:
print("Load lattice file defeated. Please make sure it is a lattice file avaliable.")
raise e
else:
allData.append(out)
try:
allData = b"".join(allData)
except Exception as e:
raise WrongOperation("Only support binary format lattice file.")
else:
return Lattice(data=allData, name=name)
else:
raise UnsupportedType(f"Expected bytes object or lattice file but got: {type_name(target)}.")
def load_args(target): ''' Load arguments from file. Args: <target>:file path. Return: an ArgumentParser object. ''' fileName = list_files(target) assert len(fileName) == 1, "Cannot load auguments from multiple files." global args args.reset() args.load(fileName[0]) return args
def __read_data_from_file(fileName, useSuffix=None):
'''
Read data from file. If the file suffix is unknown, <useSuffix> should be assigned.
'''
if useSuffix != None:
assert isinstance(useSuffix, str), "Expected <useSuffix> is a string."
useSuffix = useSuffix.strip().lower()[-3:]
else:
useSuffix = ""
assert useSuffix in [
"", "scp", "ark", "npy"
], f'Expected <useSuffix> is "ark", "scp" or "npy" but got "{useSuffix}".'
if isinstance(fileName, str):
if os.path.isdir(fileName):
raise WrongOperation(
f"Expected file name but got a directory:{fileName}.")
else:
allFiles = list_files(fileName)
else:
raise UnsupportedType(
f'Expected <fileName> is file name-like string but got a {type_name(fileName)}.'
)
allData_bytes = BytesMatrix()
allData_numpy = NumpyMatrix()
def loadNpyFile(fileName):
try:
temp = np.load(fileName, allow_pickle=True)
data = {}
#totalSize = 0
for utt_mat in temp:
data[utt_mat[0]] = utt_mat[1]
#totalSize += sys.getsizeof(utt_mat[1])
#if totalSize > 10000000000:
# print('Warning: Data is extramely large. It could not be used correctly sometimes.')
except:
raise UnsupportedType(
f'Expected "npy" data with exkaldi format but got {fileName}.')
else:
return NumpyMatrix(data)
def loadArkScpFile(fileName, suffix):
ExkaldiInfo.vertify_kaldi_existed()
if suffix == "ark":
cmd = 'copy-feats ark:'
else:
cmd = 'copy-feats scp:'
cmd += '{} ark:-'.format(fileName)
out, err, cod = run_shell_command(cmd,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
if (isinstance(cod, int) and cod != 0) or out == b'':
print(err.decode())
raise KaldiProcessError('Copy feat defeated.')
else:
#if sys.getsizeof(out) > 10000000000:
# print('Warning: Data is extramely large. It could not be used correctly sometimes.')
return BytesMatrix(out)
for fileName in allFiles:
sfx = fileName[-3:].lower()
if sfx == "npy":
allData_numpy += loadNpyFile(fileName)
elif sfx in ["ark", "scp"]:
allData_bytes += loadArkScpFile(fileName, sfx)
elif useSuffix == "npy":
allData_numpy += loadNpyFile(fileName)
elif useSuffix in ["ark", "scp"]:
allData_bytes += loadArkScpFile(fileName, useSuffix)
else:
raise UnsupportedType(
'Unknown file suffix. You can assign the <useSuffix> with "scp", "ark" or "npy".'
)
if useSuffix == "":
if allFiles[0][-3:].lower() == "npy":
result = allData_numpy + allData_bytes.to_numpy()
else:
result = allData_bytes + allData_numpy.to_bytes()
elif useSuffix == "npy":
result = allData_numpy + allData_bytes.to_numpy()
else:
result = allData_bytes + allData_numpy.to_bytes()
result.check_format()
return result
def load_ali(target, aliType=None, name="ali", hmm=None):
'''
Load alignment data.
Args:
<target>: Python dict object, bytes object, exkaldi alignment object, kaldi alignment file or .npy file.
<aliType>: None, or one of 'transitionID', 'phoneID', 'pdfID'. It will return different alignment object.
<name>: a string.
<hmm>: file path or exkaldi HMM object.
Return:
exkaldi alignment data objects.
'''
assert isinstance(
name, str) and len(name) > 0, "Name shoud be a string avaliable."
ExkaldiInfo.vertify_kaldi_existed()
def transform(data, cmd):
out, err, cod = run_shell_command(cmd,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
inputs=data)
if (isinstance(cod, int) and cod != 0) and out == b'':
print(err.decode())
raise KaldiProcessError('Failed to transform alignment.')
else:
result = {}
sp = BytesIO(out)
for line in sp.readlines():
line = line.decode()
line = line.strip().split()
utt = line[0]
matrix = np.array(line[1:], dtype=np.int32)
result[utt] = matrix
return results
if isinstance(target, dict):
if aliType is None:
result = NumpyAlignment(target, name)
elif aliType == "transitionID":
result = NumpyAlignmentTrans(target, name)
elif aliType == "phoneID":
result = NumpyAlignmentPhone(target, name)
elif aliType == "pdfID":
result = NumpyAlignmentPdf(target, name)
else:
raise WrongOperation(
f"<aliType> should be None, 'transitionID', 'phoneID' or 'pdfID' but got {aliType}."
)
result.check_format()
return result
elif type_name(target) in [
"NumpyAlignment", "NumpyAlignmentTrans", "NumpyAlignmentPhone",
"NumpyAlignmentPdf", "BytesAlignmentTrans"
]:
result = copy.deepcopy(target)
result.rename(name)
return result
elif isinstance(target, str):
allFiles = list_files(target)
results = {
"NumpyAlignment": NumpyAlignment(),
"NumpyAlignmentTrans": NumpyAlignmentTrans(),
"NumpyAlignmentPhone": NumpyAlignmentPhone(),
"NumpyAlignmentPdf": NumpyAlignmentPdf(),
"BytesAlignmentTrans": BytesAlignmentTrans(),
}
for fileName in allFiles:
fileName = os.path.abspath(fileName)
if fileName.endswith(".npy"):
temp = __read_data_from_file(fileName, "npy")
if aliType is None:
temp = NumpyAlignment(temp.data)
results["NumpyAlignment"] += temp
elif aliType == "transitionID":
temp = NumpyAlignmentTrans(temp.data)
results["NumpyAlignmentTrans"] += temp
elif aliType == "phoneID":
temp = NumpyAlignmentPhone(temp.data)
results["NumpyAlignmentPhone"] += temp
elif aliType == "pdfID":
temp = NumpyAlignmentPdf(temp.data)
results["NumpyAlignmentPdf"] += temp
else:
raise WrongOperation(
f"<aliType> should be None, 'transitionID','phoneID' or 'pdfID' but got {aliType}."
)
else:
if fileName.endswith('.gz'):
cmd = f'gunzip -c {fileName}'
else:
cmd = f'cat {fileName}'
if aliType is None or aliType == "transitionID":
out, err, cod = run_shell_command(cmd,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
if (isinstance(cod, int) and cod != 0) or out == b'':
print(err.decode())
raise ShellProcessError(
"Failed to get the alignment data from file.")
else:
temp = BytesAlignmentTrans(out)
results["BytesAlignmentTrans"] += temp
else:
temp = tempfile.NamedTemporaryFile("wb+")
try:
if type_name(hmm) in ("HMM", "MonophoneHMM",
"TriphoneHMM"):
hmm.save(temp)
hmmFileName = temp.name
elif isinstance(hmm, str):
if not os.path.isfile(hmm):
raise WrongPath(f"No such file:{hmm}.")
hmmFileName = hmm
else:
raise UnsupportedType(
f"<hmm> should be a filePath or exkaldi HMM and its sub-class object. but got {type_name(hmm)}."
)
if aliType == "phoneID":
cmd += f" | ali-to-phones --per-frame=true {hmmFileName} ark:- ark,t:-"
temp = transform(None, cmd)
temp = NumpyAlignmentPhone(temp)
results["NumpyAlignmentPhone"] += temp
elif target == "pdfID":
cmd = f" | ali-to-pdf {hmmFileName} ark:- ark,t:-"
temp = transform(None, cmd)
temp = NumpyAlignmentPdf(temp)
results["NumpyAlignmentPdf"] += temp
else:
raise WrongOperation(
f"<target> should be 'trainsitionID', 'phoneID' or 'pdfID' but got {target}."
)
finally:
temp.close()
finalResult = []
for obj in results.values():
if not obj.is_void:
obj.rename(name)
finalResult.append(obj)
if len(finalResult) == 0:
raise WrongOperation(
"<target> dose not include any data avaliable.")
elif len(finalResult) == 1:
finalResult = finalResult[0]
return finalResult
def load_ali(target, aliType="transitionID", name="ali", hmm=None):
'''
Load alignment data.
Args:
<target>: Python dict object,bytes object,exkaldi alignment object,kaldi alignment file or .npy file.
<aliType>: None,or one of 'transitionID','phoneID','pdfID'. It will return different alignment object.
<name>: a string.
<hmm>: file path or exkaldi HMM object.
Return:
exkaldi alignment objects.
'''
declare.is_valid_string("name", name)
declare.is_instances("aliType", aliType,
[None, "transitionID", "phoneID", "pdfID"])
declare.kaldi_existed()
def transform(data, cmd):
out, err, cod = run_shell_command(cmd,
stdin="PIPE",
stdout="PIPE",
stderr="PIPE",
inputs=data)
if (isinstance(cod, int) and cod != 0) and out == b'':
raise KaldiProcessError('Failed to transform alignment.',
err.decode())
else:
result = {}
sp = BytesIO(out)
for line in sp.readlines():
line = line.decode()
line = line.strip().split()
utt = line[0]
matrix = np.array(line[1:], dtype=np.int32)
result[utt] = matrix
return result
if isinstance(target, dict):
if aliType is None:
result = NumpyAli(target, name)
elif aliType == "transitionID":
result = NumpyAliTrans(target, name)
elif aliType == "phoneID":
result = NumpyAliPhone(target, name)
elif aliType == "pdfID":
result = NumpyAliPdf(target, name)
else:
raise WrongOperation(
f"<aliType> should be None,'transitionID','phoneID' or 'pdfID' but got {aliType}."
)
result.check_format()
return result
elif isinstance(target, (NumpyAli, NumpyAliTrans, BytesAliTrans)):
result = copy.deepcopy(target)
result.rename(name)
return result
elif isinstance(target, IndexTable):
result = target.fetch(arkType="ali")
if aliType in ["phoneID", "pdfID"]:
result = result.to_numpy(aliType, hmm)
result.rename(name)
return result
elif isinstance(target, str):
allFiles = list_files(target)
numpyAli = {}
bytesAli = []
for fileName in allFiles:
fileName = fileName.strip()
if fileName.endswith(".npy"):
try:
temp = np.load(fileName, allow_pickle=True)
numpyAli.update(temp)
except:
raise UnsupportedType(
f'This is not a valid Exkaldi npy file: {fileName}.')
else:
if fileName.endswith('.gz'):
cmd = f'gunzip -c {fileName}'
else:
cmd = f'cat {fileName}'
if aliType is None or aliType == "transitionID":
out, err, cod = run_shell_command(cmd,
stdout="PIPE",
stderr="PIPE")
if (isinstance(cod, int) and cod != 0) or out == b'':
raise ShellProcessError(
f"Failed to get the alignment data from file: {fileName}.",
err.decode())
else:
bytesAli.append(out)
else:
with FileHandleManager() as fhm:
declare.is_potential_hmm("hmm", hmm)
if not isinstance(hmm, str):
hmmTemp = fhm.create("wb+")
hmm.save(hmmTemp)
hmm = hmmTemp.name
if aliType == "phoneID":
cmd += f" | ali-to-phones --per-frame=true {hmm} ark:- ark,t:-"
temp = transform(None, cmd)
else:
cmd += f" | ali-to-pdf {hmm} ark:- ark,t:-"
temp = transform(None, cmd)
numpyAli.update(temp)
bytesAli = b"".join(bytesAli)
if aliType is None:
if len(numpyAli) == 0:
return BytesAliTrans(bytesAli, name=name)
elif len(bytesAli) == 0:
return NumpyAli(numpyAli, name=name)
else:
result = NumpyAliTrans(numpyAli) + BytesAliTrans(bytesAli)
result.rename(name)
return result
elif aliType == "transitionID":
if len(numpyAli) == 0:
return BytesAliTrans(bytesAli, name=name)
elif len(bytesAli) == 0:
return NumpyAliTrans(numpyAli, name=name)
else:
result = NumpyAliTrans(numpyAli) + BytesAliTrans(bytesAli)
result.rename(name)
return result
elif aliType == "phoneID":
return NumpyAliPhone(numpyAli, name=name)
else:
return NumpyAliPdf(numpyAli, name=name)
else:
raise UnsupportedType(
f"<target> should be dict,file name or exkaldi alignment or index table object but got: {type_name(target)}."
)
def __read_data_from_file(fileName, useSuffix=None):
'''
Read data from file. If the file suffix is unknown,<useSuffix> is necessary.
'''
declare.kaldi_existed()
if useSuffix != None:
declare.is_valid_string("useSuffix", useSuffix)
useSuffix = useSuffix.strip().lower()[-3:]
declare.is_instances("useSuffix", useSuffix, ["ark", "scp", "npy"])
else:
useSuffix = ""
allFiles = list_files(fileName)
allData_bytes = []
allData_numpy = {}
def loadNpyFile(fileName):
try:
temp = np.load(fileName, allow_pickle=True)
data = {}
for utt_mat in temp:
assert isinstance(utt_mat[0], str) and isinstance(
utt_mat[1], np.ndarray)
data[utt_mat[0]] = utt_mat[1]
except:
raise UnsupportedType(
f'This is not a valid Exkaldi npy file: {fileName}.')
else:
return data
def loadArkScpFile(fileName, suffix):
declare.kaldi_existed()
if suffix == "ark":
cmd = 'copy-feats ark:'
else:
cmd = 'copy-feats scp:'
cmd += '{} ark:-'.format(fileName)
out, err, cod = run_shell_command(cmd, stdout="PIPE", stderr="PIPE")
if (isinstance(cod, int) and cod != 0) or out == b'':
raise KaldiProcessError('Failed to read archive table.',
err.decode())
else:
#if sys.getsizeof(out) > 10000000000:
# print('Warning: Data is extramely large. We don't recommend use load_index_table to replace it.')
return out
for fileName in allFiles:
sfx = fileName.strip()[-3:].lower()
if sfx == "npy":
allData_numpy.update(loadNpyFile(fileName))
elif sfx in ["ark", "scp"]:
allData_bytes.append(loadArkScpFile(fileName, sfx))
elif useSuffix == "npy":
allData_numpy.update(loadNpyFile(fileName))
elif useSuffix in ["ark", "scp"]:
allData_bytes.append(loadArkScpFile(fileName, sfx))
else:
raise UnsupportedType(
'Unknown file suffix. You can appoint the <useSuffix> option with "scp","ark" or "npy".'
)
allData_bytes = b"".join(allData_bytes)
if useSuffix == "":
useSuffix = allFiles[0].strip()[-3:].lower()
if useSuffix == "npy":
dataType = "numpy"
else:
dataType = "bytes"
return allData_bytes, allData_numpy, dataType
def load_index_table(target, name="index", useSuffix=None):
'''
Load an index table from dict,or archive table file.
Args:
<target>: dict object,.ark or .scp file,IndexTable object,bytes archive object.
<name>: a string.
<useSuffix>: "ark" or "scp". We will check the file type by its suffix.
But if <target> is file path and not default suffix (ark or scp),you have to declare which type it is.
Return:
an exkaldi IndexTable object.
'''
newTable = IndexTable(name=name)
if type_name(target) == "dict":
for key, value in target.items():
if isinstance(value, (list, tuple)):
assert len(value) in [
3, 4
], f"Expected (frames,start index,data size[,file path]) but {value} does not match."
newTable[key] = newTable.spec(*value)
elif type_name(value) == "Index":
newTable[key] = value
else:
raise WrongDataFormat(
f"Expected list or tuple but got wrong index info format: {value}."
)
return newTable
elif type_name(target) == "IndexTable":
newTable.update(target)
return newTable
elif isinstance(target, BytesArchive):
newTable.update(target.indexTable)
return newTable
else:
fileList = list_files(target)
if useSuffix is not None:
declare.is_valid_string("useSuffix", useSuffix)
useSuffix = useSuffix.strip()[-3:].lower()
declare.is_instances("useSuffix", useSuffix, ["ark", "scp"])
else:
useSuffix = ""
for fileName in fileList:
if fileName.rstrip().endswith(".ark"):
t = __read_index_table_from_ark_file(fileName)
elif fileName.rstrip().endswith(".scp"):
t = __read_index_table_from_scp_file(fileName)
elif useSuffix == "ark":
t = __read_index_table_from_ark_file(fileName)
elif useSuffix == "scp":
t = __read_index_table_from_scp_file(fileName)
else:
raise UnsupportedType(
"Unknown file suffix. Specify <useSuffix> please.")
newTable.update(t)
return newTable
def __compute_feature(target,kaldiTool,useSuffix=None,name="feat",outFile=None):
'''
The base funtion to compute feature.
'''
declare.kaldi_existed()
if useSuffix != None:
declare.is_valid_string("useSuffix",useSuffix)
useSuffix = useSuffix.strip().lower()[-3:]
declare.is_instances("useSuffix",useSuffix,["scp","wav"])
else:
useSuffix = ""
targets,kaldiTools,useSuffixs,names,outFiles = check_multiple_resources(target,kaldiTool,useSuffix,name,outFile=outFile)
# pretreatment
fromSegment = False
with FileHandleManager() as fhm:
segments = []
for index,kaldiTool,target,useSuffix,name in zip(range(len(outFiles)),kaldiTools,targets,useSuffixs,names):
declare.is_classes("target",target,["str","ListTable","WavSegment"])
declare.is_valid_string("name",name)
if isinstance(target,str):
allFiles = list_files(target)
target = ListTable()
for filePath in allFiles:
filePath = filePath.strip()
if filePath[-4:].lower() == ".wav":
fileName = os.path.basename(filePath)
uttID = fileName[0:-4].replace(".","")
target[uttID] = filePath
elif filePath[-4:].lower() == '.scp':
target += load_list_table(filePath)
elif "wav" == useSuffix:
fileName = os.path.basename(filePath)
uttID = fileName.replace(".","")
target[uttID] = filePath
elif "scp" == useSuffix:
target += load_list_table(filePath)
else:
raise UnsupportedType('Unknown file suffix. You can declare whether <useSuffix> is "wav" or "scp".')
if len(target) == 0:
raise WrongDataFormat("There did not include any data to compute data in target.")
targets[index] = target
elif type_name(target) == "WavSegment":
segTemp = fhm.create("w+",suffix=".seg",encode="utf-8")
target.save(segTemp)
segments.append(segTemp.name)
targets[index] = target.detach_wav()
fromSegment = True
if fromSegment:
# define the command pattern
cmdPattern = "extract-segments scp:{wavFile} {segment} ark:- | {kaldiTool} ark:- ark:{outFile}"
# define resources
resources = {"wavFile":targets,"segment":segments,"kaldiTool":kaldiTools,"outFile":outFiles}
else:
# define the command pattern
cmdPattern = "{kaldiTool} scp:{wavFile} ark:{outFile}"
# define resources
resources = {"wavFile":targets,"kaldiTool":kaldiTools,"outFile":outFiles}
# Run
return run_kaldi_commands_parallel(resources,cmdPattern,analyzeResult=True,generateArchive="feat",archiveNames=names)
