def replace_pronunciations(target, source, env):
"""
Takes two pronunciation files, and replaces pronunciations in the first with those from the second,
for overlapping words. Returns a new vocabulary file and pronunciation file.
"""
with meta_open(source[0].rstr()) as old_fd, meta_open(source[1].rstr()) as repl_fd:
old = Pronunciations(old_fd)
repl = Pronunciations(repl_fd)
logging.info("Old pronunciations: %s", old)
logging.info("Replacement pronunciations: %s", repl)
old.replace_by(repl)
logging.info("New pronunciations: %s", old)
with meta_open(target[0].rstr(), "w") as voc_ofd, meta_open(target[1].rstr(), "w") as pron_ofd:
voc_ofd.write(old.format_vocabulary())
pron_ofd.write(old.format())
return None
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 pronunciations_to_vocabulary(target, source, env):
with meta_open(source[0].rstr()) as ifd:
d = Pronunciations(ifd)
with meta_open(target[0].rstr(), "w") as ofd:
ofd.write(d.format_vocabulary())
return None
