def augment_language_model(target, source, env):
"""
Input: old language model, old pronunciations, new pronunciations|
** old language model, old pronunciations, new pronunciations
Output: new language model, new vocab, new pronunciations
"""
#from arpabo import Arpabo, Pronunciations
weighted = len(source) == 5
old_prons = Pronunciations(meta_open(source[0].rstr()))
old_lm = Arpabo(meta_open(source[1].rstr()))
new_prons = Pronunciations(meta_open(source[2].rstr()))
mass = source[-1].read()
logging.info("Old LM: %s", old_lm)
logging.info("Old Pronunciations: %s", old_prons)
logging.info("Words to add: %s", new_prons)
if weighted:
new_probs = ProbabilityList(meta_open(source[3].rstr()))
logging.info("Words to add (probabilities): %s", new_probs)
old_prons.add_entries(new_prons)
if weighted:
old_lm.add_unigrams_with_probs(new_probs, mass)
else:
old_lm.add_unigrams(new_prons.get_words(), mass)
logging.info("New Pronunciations: %s", old_prons)
logging.info("New LM: %s", old_lm)
logging.info("New words have weight %s", old_lm.get_probability_of_words(new_prons.get_words()))
logging.info("Old words have weight %s", old_lm.get_probability_of_not_words(new_prons.get_words()))
with meta_open(target[0].rstr(), "w") as new_vocab, meta_open(target[1].rstr(), "w") as new_prons, meta_open(target[2].rstr(), "w") as new_lm:
new_lm.write(old_lm.format())
new_vocab.write(old_prons.format_vocabulary())
new_prons.write(old_prons.format())
return None
def pronunciation_performance(target, source, env):
with meta_open(source[0].rstr()) as gold_fd, meta_open(source[1].rstr()) as gen_fd:
tp, fp, fn = 0, 0, 0
gold = Pronunciations(gold_fd)
gen = Pronunciations(gen_fd)
logging.info("gold phone inventory: %s", " ".join(gold.phones()))
logging.info("generated phone inventory: %s", " ".join(gen.phones()))
for x in gen.get_words().intersection(gold.get_words()):
gold_prons = set(map(tuple, [map(str.lower, y) for y in gold[x].values()]))
gen_prons = set(map(tuple, [map(str.lower, y) for y in gen[x].values()]))
for go_p in gold_prons:
if go_p in gen_prons:
tp += 1
else:
fn += 1
for ge_p in gen_prons:
if ge_p not in gold_prons:
fp += 1
prec = float(tp) / (tp + fp)
rec = float(tp) / (tp + fn)
f = 2 * (prec * rec) / (prec + rec)
with meta_open(target[0].rstr(), "w") as ofd:
ofd.write("%f %f %f\n" % (prec, rec, f))
return None
