def __init__(self, logfile=None):
"""
"""
sppasBase.__init__(self, logfile)
self.intsint = Intsint()
def __init__(self, logfile=None):
"""
Constructor.
@param logfile (sppasLog) is a log file utility class member.
"""
sppasBase.__init__(self, logfile)
self.momel = Momel()
self.PAS_TRAME = 10.
def __init__(self, resourcefile, logfile=None):
"""
Create a new sppasRepetition instance.
@param resourcefile is either the lemma dictionary or the list of stop-words.
Attention: the extention of the resource file name is very important:
must be ".stp" for stop-words and ".lem" for lemmas (case-sensitive)!
"""
sppasBase.__init__(self, logfile)
# Members
self._use_lemmatize = True # Lemmatize the input
self._use_stopwords = True # Add specific stopwords of the input
self._empan = 5 # Detection length (nb of IPUs; 1=current IPU)
self._alpha = 0.5 # Specific stop-words threshold coefficient
self.logfile = logfile
self.lemmatizer = None
self.stopwords = None
# Create the lemmatizer instance
try:
lemmafile = resourcefile.replace(".stp", ".lem")
self.lemmatizer = LemmaDict(lemmafile)
except Exception:
self._use_lemmatize = False
if (self._use_lemmatize is True and self.lemmatizer.get_size() == 0) or self._use_lemmatize is False:
if logfile is not None:
logfile.print_message("Lemmatization disabled.",indent=2,status=3)
else:
print " ... ... [ INFO ] Lemmatization disabled."
self._use_lemmatize = False
# Create the list of stop words (list of non-relevant words)
try:
stopfile = resourcefile.replace(".lem", ".stp")
self.stopwords = WordsList(filename=resourcefile, nodump=True)
if self.stopwords.get_size() == 0:
self._use_stopwords = False
except Exception:
self.stopwords = WordsList()
#if (self._use_stopwords is True and self.stopwords.get_size() == 0) or self._use_stopwords is False:
if self._use_stopwords is False:
if logfile is not None:
logfile.print_message("StopWords disabled.",indent=2,status=3)
else:
print " ... ... [ INFO ] StopWords disabled."
def __init__(self, model, modelL1=None, logfile=None):
"""
Create a new sppasAlign instance.
@param model (str) the acoustic model directory name of the language of the text
@param modelL1 (str) the acoustic model directory name of the mother language of the speaker
@param logfile (sppasLog)
"""
sppasBase.__init__(self, logfile)
# Members: self.alignio
self.fix_segmenter( model,modelL1 )
self.reset()
def __init__(self, model, logfile=None):
"""
Create a new sppasChunks instance.
@param model (str) the acoustic model directory name of the language of the text
@param modelL1 (str) the acoustic model directory name of the mother language of the speaker
@param logfile (sppasLog)
"""
sppasBase.__init__(self, logfile)
self.chunks = Chunks(model)
self._options["clean"] = True # Remove temporary files
self._options["silences"] = self.chunks.get_silences()
self._options["anchors"] = self.chunks.get_anchors()
self._options["ngram"] = self.chunks.get_ngram_init()
self._options["ngrammin"] = self.chunks.get_ngram_min()
self._options["windelay"] = self.chunks.get_windelay_init()
self._options["windelaymin"] = self.chunks.get_windelay_min()
self._options["chunksize"] = self.chunks.get_chunk_maxsize()
def __init__(self, dictfilename, mapfile=None, logfile=None):
"""
Constructor.
@param dictfilename (str) is the pronunciation dictionary file name
(HTK-ASCII format, utf8).
@param mapfile (str) is the filename of a mapping table. It is used
to generate new pronunciations by mapping phonemes of the dictionary.
@param logfile (sppasLog) is a log file utility class member.
"""
sppasBase.__init__(self, logfile)
# Pronunciation dictionary
self.maptable = None
if mapfile is not None:
self.maptable = Mapping( mapfile )
self.set_dict( dictfilename )
# List of options to configure this automatic annotation
self._options = {}
self._options['phonunk'] = False # Phonetize missing tokens
self._options['usestdtokens'] = False # Phonetize standard spelling
