if options.testSample:
mainTest(translator, loadSample(options.testSample), options)
translator.reportStats(sys.stdout)
if options.applySample:
mainApply(translator, options)
translator.reportStats(sys.stderr)
# ===========================================================================
if __name__ == '__main__':
import optparse, tool
optparser = optparse.OptionParser(usage='%prog [OPTION]... FILE...\n' +
str(__doc__),
version='%prog ' + __version__)
tool.addOptions(optparser)
SequiturTool.addTrainOptions(optparser)
optparser.add_option('-e',
'--encoding',
default='ISO-8859-15',
help='use character set encoding ENC',
metavar='ENC')
optparser.add_option('-P',
'--phoneme-to-phoneme',
action='store_true',
help='train/apply a phoneme-to-phoneme converter')
optparser.add_option(
'--test-segmental',
action='store_true',
help=
'evaluate only at segmental level, i.e. do not count syllable boundaries and stress marks'
if options.testSample:
mainTest(translator, loadSample(options.testSample), options)
translator.reportStats(sys.stdout)
if options.applySample:
mainApply(translator, options)
translator.reportStats(sys.stderr)
# ===========================================================================
if __name__ == '__main__':
import optparse, tool
optparser = optparse.OptionParser(
usage = '%prog [OPTION]... FILE...\n' + __doc__,
version = '%prog ' + __version__)
tool.addOptions(optparser)
SequiturTool.addTrainOptions(optparser)
optparser.add_option(
'-e', '--encoding', default='ISO-8859-15',
help='use character set encoding ENC', metavar='ENC')
optparser.add_option(
'-P', '--phoneme-to-phoneme', action='store_true',
help='train/apply a phoneme-to-phoneme converter')
optparser.add_option(
'--test-segmental', action='store_true',
help='evaluate only at segmental level, i.e. do not count syllable boundaries and stress marks')
optparser.add_option(
'-B', '--result', dest='testResult',
help='store test result in table FILE (for use with bootlog or R)', metavar='FILE')
optparser.add_option(
'-a', '--apply', dest='applySample',
lm = makeLmWriter(options)
else:
lm = LmDummy()
builder.build(counts, lm)
if __debug__ and False: ### TESTING
print('verifying normalization ...', file=sys.stdout)
lm2 = Lm(lm)
lm2.checkNormalisation()
if __name__ == '__main__':
import optparse, tool
options = optparse.OptionParser()
tool.addOptions(options)
options.add_option('-v', '--vocabulary')
options.add_option('-r', '--read')
options.add_option('-U',
'--count-cutoffs',
help='set count cutoff values to n_i for order i',
metavar='n_0 n_1 ...')
options.add_option('-C',
'--counts-of-counts',
help='read counts-of-counts from FILE',
metavar='FILE')
options.add_option('-M', '--order', type='int', default=3)
options.add_option('-f',
'--lm-format',
default='arpa',
help='valid choices are: arpa, estar')
counts = mappedCounts
if options.write:
countFile = misc.gOpenOut(options.write)
TextStorage.write(countFile, counts)
if options.counts_of_counts:
coc = [ countsOfCounts(mGramReduceToOrder(counts, order))
for order in range(options.order) ]
import pprint
pprint.pprint(coc, misc.gOpenOut(options.counts_of_counts))
if __name__ == '__main__':
import optparse, tool
options = optparse.OptionParser()
tool.addOptions(options)
options.add_option('-t', '--text')
options.add_option('-r', '--read', action='append')
options.add_option('-v', '--vocabulary')
options.add_option('-M', '--order', type='int', default=3)
options.add_option('-w', '--write')
options.add_option('--map-oov', action='store_true')
options.add_option('-C', '--counts-of-counts')
options.add_option('--storage-class', default='smf')
options.add_option('--memory-limit', type='int')
options, args = options.parse_args()
tool.run(main, options, args)
def getOptParser():
import optparse, tool
optparser = optparse.OptionParser(usage='%prog [OPTION]... FILE...\n' +
str(__doc__),
version='%prog ' + __version__)
tool.addOptions(optparser)
SequiturTool.addTrainOptions(optparser)
optparser.add_option('-e',
'--encoding',
default='ISO-8859-15',
help='use character set encoding ENC',
metavar='ENC')
optparser.add_option('-P',
'--phoneme-to-phoneme',
action='store_true',
help='train/apply a phoneme-to-phoneme converter')
optparser.add_option(
'--test-segmental',
action='store_true',
help=
'evaluate only at segmental level, i.e. do not count syllable boundaries and stress marks'
)
optparser.add_option(
'-B',
'--result',
dest='testResult',
help='store test result in table FILE (for use with bootlog or R)',
metavar='FILE')
optparser.add_option(
'-a',
'--apply',
dest='applySample',
help='apply grapheme-to-phoneme conversion to words read from FILE',
metavar='FILE')
optparser.add_option('-w',
'--word',
dest='applyWord',
help='apply grapheme-to-phoneme conversion to word',
metavar='string')
optparser.add_option(
'-V',
'--variants-mass',
type='float',
help=
'generate pronunciation variants until \sum_i p(var_i) >= Q (only effective with --apply)',
metavar='Q')
optparser.add_option(
'--variants-number',
type='int',
help=
'generate up to N pronunciation variants (only effective with --apply)',
metavar='N')
optparser.add_option(
'-f',
'--fake',
dest='fakeTranslator',
help=
'use a translation memory (read from sample FILE) instead of a genuine model (use in combination with -x to evaluate two files against each other)',
metavar='FILE')
optparser.add_option('--stack-limit',
type='int',
help='limit size of search stack to N elements',
metavar='N')
return optparser
