def filter_by(target, source, env):
"""
Keep words in first vocabulary file that also occur in second vocabulary file
"""
with meta_open(source[0].rstr()) as ifdA, meta_open(source[1].rstr()) as ifdB:
first = Vocabulary(ifdA)
second = Vocabulary(ifdB)
filtered = first.filter_by(second)
with meta_open(target[0].rstr(), "w") as ofd:
ofd.write(filtered.format())
return None
def probability_list_to_vocabulary(target, source, env):
with meta_open(source[0].rstr()) as ifd:
probs = ProbabilityList(ifd)
with meta_open(target[0].rstr(), "w") as ofd:
vocab = Vocabulary.from_set(probs.get_words())
ofd.write(vocab.format())
return None
def text_to_vocabulary(target, source, env):
lower_case = len(source) == 1 or source[1].read()
with meta_open(source[0].rstr()) as ifd:
if lower_case:
words = set(ifd.read().lower().split())
else:
words = set(ifd.read().split())
vocab = Vocabulary.from_set([w for w in words if "_" not in w and not w.startswith("-") and not w.endswith("-")])
with meta_open(target[0].rstr(), "w") as ofd:
ofd.write(vocab.format())
return None
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