def train_alignment(corpus='cmudict',
stress="unstressed",
subset=False,
delete_prob=0.01,
insert_prob=0.01,
kerberos_cmd=None):
### load the corpus and dict of allowables
ab_pairs = load_pronunciations()
alignment_scores = load_allowables(delete_prob=delete_prob,
insert_prob=insert_prob)
### are we testing with a subset?
if subset:
# test with 0.1% of the corpus
ab_pairs = random.sample(ab_pairs, len(ab_pairs) / 1000)
ab_pairs.sort(cmp=lambda x, y: cmp(x[0], y[0]))
# initialize the EM with the corpus and allowables
em = ViterbiEM(ab_pairs, alignment_scores, max_iterations=100)
# check to see if we've got a saved model
em_fname = construct_model_fname(corpus, stress, subset)
try:
em.load(em_fname)
except IOError:
pass
if kerberos_cmd is not None:
os.system(kerberos_cmd)
# run the Viterbi aligner EM, saving as we go
while True:
em.run_EM(1)
em.save(em_fname)
if em.converged:
break
if em.iteration_number > em.max_iterations:
break
return em
def train_alignment(corpus='cmudict',
stress="unstressed",
subset=False,
delete_prob=0.01,
insert_prob=0.01,
kerberos_cmd=None):
### load the corpus and dict of allowables
ab_pairs = load_pronunciations()
alignment_scores = load_allowables(delete_prob=delete_prob,
insert_prob=insert_prob)
### are we testing with a subset?
if subset:
# test with 0.1% of the corpus
ab_pairs = random.sample(ab_pairs, len(ab_pairs)/1000)
ab_pairs.sort(cmp = lambda x,y: cmp(x[0], y[0]))
# initialize the EM with the corpus and allowables
em = ViterbiEM(ab_pairs, alignment_scores, max_iterations=100)
# check to see if we've got a saved model
em_fname = construct_model_fname(corpus, stress, subset)
try: em.load(em_fname)
except IOError: pass
if kerberos_cmd is not None:
os.system(kerberos_cmd)
# run the Viterbi aligner EM, saving as we go
while True:
em.run_EM(1)
em.save(em_fname)
if em.converged:
break
if em.iteration_number > em.max_iterations:
break
return em
