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 top_words(target, source, env):
args = source[-1].read()
with meta_open(source[0].rstr()) as words_ifd, meta_open(source[1].rstr()) as pron_ifd:
top = ProbabilityList(words_ifd).get_top_n(args["COUNT"])
prons = Pronunciations(pron_ifd)
prons.filter_by(top)
with meta_open(target[0].rstr(), "w") as words_ofd, meta_open(target[1].rstr(), "w") as pron_ofd:
words_ofd.write(top.format())
pron_ofd.write(prons.format())
return None
def filter_babel_gum(target, source, env):
with meta_open(source[0].rstr()) as pron_ifd, meta_open(source[1].rstr()) as prob_ifd, meta_open(source[2].rstr()) as lim_ifd:
pron = Pronunciations(pron_ifd)
logging.info("Old pronunciations: %s", pron)
prob = ProbabilityList(prob_ifd)
logging.info("Old probabilities: %s", prob)
filt = Vocabulary(lim_ifd)
logging.info("Correct words: %s", filt)
pron.filter_by(filt)
logging.info("New pronunciations: %s", pron)
prob.filter_by(filt)
logging.info("New probabilities: %s", prob)
with meta_open(target[0].rstr(), "w") as pron_ofd, meta_open(target[1].rstr(), "w") as prob_ofd:
pron_ofd.write(pron.format())
prob_ofd.write(prob.format())
return None
