def setup_segments(self, ):
"""Create segments in data directory"""
target = os.path.join(self._output_path(), 'segments')
# even if there is only one utterance per wav, we add the
# tstart/tstop in the segment file
CorpusSaver.save_segments(self.corpus, target, force_timestamps=True)
def save(self, path, no_wavs=False, copy_wavs=True, force=False):
"""Save the corpus to the directory `path`
:param str path: The output directory is assumed to be a non
existing directory (or use force=True to overwrite it).
:param bool no_wavs: when True, dont save the wavs (ie don't
write wavs subdir in `path`)
:param bool copy_wavs: when True, make a copy of the wavs
instead of symbolic links
:param bool force: when True, overwrite `path` if it is
already existing
:raise: OSError if force=False and `path` already exists
"""
self.log.info('saving corpus to %s', path)
if force and os.path.exists(path):
self.log.warning('overwriting existing path: %s', path)
utils.remove(path)
CorpusSaver.save(self, path, no_wavs=no_wavs, copy_wavs=copy_wavs)
def setup_silences(self):
"""Create data/local/self.name/{silences, optional_silence}.txt"""
local_path = self._local_path()
CorpusSaver.save_silences(
self.corpus, os.path.join(local_path, 'silence_phones.txt'))
target = os.path.join(local_path, 'optional_silence.txt')
with open_utf8(target, 'w') as out:
out.write(u'SIL\n')
def setup_utt2spk(self):
"""Create utt2spk and spk2utt in data directory"""
target = os.path.join(self._output_path(), 'utt2spk')
CorpusSaver.save_utt2spk(self.corpus, target)
# create spk2utt
target = os.path.join(self._output_path(), 'spk2utt')
with open_utf8(target, 'w') as out:
for spk, utt in sorted(self.corpus.spk2utt().iteritems()):
out.write(u'{} {}\n'.format(spk, ' '.join(sorted(utt))))
def setup_lexicon(self):
"""Create data/local/self.name/lexicon.txt"""
target = os.path.join(self._local_path(), 'lexicon.txt')
CorpusSaver.save_lexicon(self.corpus, target)
return target
def setup_wav_folder(self):
"""using a symbolic link to avoid copying voluminous data"""
target = os.path.join(self.recipe_dir, 'wavs')
CorpusSaver.save_wavs(self.corpus, target)
def setup_text(self):
"""Create text in data directory"""
target = os.path.join(self._output_path(), 'text')
CorpusSaver.save_text(self.corpus, target)
return target
def setup_variants(self):
"""Create data/local/`name`/extra_questions.txt"""
target = os.path.join(self._local_path(), 'extra_questions.txt')
CorpusSaver.save_variants(self.corpus, target)
def setup_segments(self,):
"""Create segments in data directory"""
target = os.path.join(self._output_path(), 'segments')
# write only if starts and stops are specified in segments.txt
if self.corpus.has_several_utts_per_wav():
CorpusSaver.save_segments(self.corpus, target)