def test_dict(self):
d = DictPron( DICT_FRA )
self.assertTrue( d.is_unk('azerty') )
self.assertFalse( d.is_unk('il_y_a') )
self.assertFalse( d.is_unk(u'être') )
self.assertEqual( d.get_pron(u'sil'), "s.i.l" )
self.assertEqual( d.get_pron(u'azerty'), "UNK" )
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 )
