def filter_words(target, source, env):
"""
Takes a coherent language model, pronunciation file and vocabulary file, and a second
vocabulary file, and returns a coherent language model, pronunciation file and vocabulary
file limited to the words in the second vocabulary file.
The language model probabilities are scaled such that unigrams sum to one. ***
"""
with meta_open(source[0].rstr()) as voc_fd, meta_open(source[1].rstr()) as pron_fd, meta_open(source[2].rstr()) as lm_fd, meta_open(source[3].rstr()) as lim_fd:
lm = Arpabo(lm_fd)
pron = Pronunciations(pron_fd)
voc = Vocabulary(voc_fd)
lim = Vocabulary(lim_fd)
logging.info("Original vocabulary: %s", voc)
logging.info("Original pronunciations: %s", pron)
logging.info("Original LM: %s", lm)
logging.info("Limiting vocabulary: %s", lim)
logging.info("Vocabulary to remove has mass: %s", lm.get_probability_of_not_words(lim.get_words()))
logging.info("Vocabulary to remain has mass: %s", lm.get_probability_of_words(lim.get_words()))
lm.filter_by(lim)
pron.filter_by(lim)
voc.filter_by(lim)
logging.info("New vocabulary: %s", voc)
logging.info("New pronunciations: %s", pron)
logging.info("New LM: %s", lm)
with meta_open(target[0].rstr(), "w") as voc_ofd, meta_open(target[1].rstr(), "w") as pron_ofd, meta_open(target[2].rstr(), "w") as lm_ofd:
voc_ofd.write(voc.format())
pron_ofd.write(pron.format())
lm_ofd.write(lm.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