def gen_slm_dependencies(self, basename, N=3):
"""
Generate the dependencies (slm, dictionary) for julius.
@param basename (str - IN) the base name of the slm file and of the dictionary file
@param N (int) Language model N-gram length.
"""
dictname = basename + ".dict"
slmname = basename + ".arpa"
phoneslist = self._phones.split()
tokenslist = self._tokens.split()
dictpron = DictPron()
for token,pron in zip(tokenslist,phoneslist):
for variant in pron.split("|"):
dictpron.add_pron( token, variant.replace("-"," ") )
if dictpron.is_unk(START_SENT_SYMBOL) is True:
dictpron.add_pron( START_SENT_SYMBOL, "sil" )
if dictpron.is_unk(END_SENT_SYMBOL) is True:
dictpron.add_pron( END_SENT_SYMBOL, "sil" )
dictpron.save_as_ascii( dictname, False )
# Write the SLM
model = NgramsModel(N)
model.append_sentences( [self._tokens] )
probas = model.probabilities( method="logml" )
arpaio = ArpaIO()
arpaio.set( probas )
arpaio.save( slmname )
def load_from_arpa(self, filename):
"""
Load the model from an ARPA-ASCII file.
@param filename (str - IN) Filename from which to read the model.
"""
arpaio = ArpaIO()
self.model = arpaio.load(filename)
def save_as_arpa(self, filename):
"""
Save the model into an ARPA-ASCII file.
@param filename (str - OUT) Filename in which to write the model.
"""
arpaio = ArpaIO()
arpaio.set( self.model )
arpaio.save( filename )
def testARPA(self):
fn1 = os.path.join(TEMP,"model1.arpa")
fn2 = os.path.join(TEMP,"model2.arpa")
model = NgramsModel(3)
model.count( self.corpusfile )
probas = model.probabilities("logml")
arpaio = ArpaIO()
arpaio.set( probas )
arpaio.save( fn1 )
slm1 = SLM()
slm1.load_from_arpa( fn1 )
slm1.save_as_arpa( fn2 )
slm2 = SLM()
slm2.load_from_arpa( fn2 )
m1 = slm1.model
m2 = slm2.model
self.assertTrue( compare(m1,m2) )
# ----------------------------------------------------------------------------
# Main program
# ----------------------------------------------------------------------------
# ---------------------------------
# 1. Create a NgramsModel
model = NgramsModel( args.n )
if args.r:
model.set_vocab( args.r )
# ---------------------------------
# 2. Estimate counts of each n-gram
model.count( *(args.i) )
# ---------------------------------
# 3. Estimate probabilities
probas = model.probabilities( args.m )
# ---------------------------------
# 4. Write in an ARPA file
arpaio = ArpaIO()
arpaio.set( probas )
arpaio.save( args.o )
# ---------------------------------------------------------------------------