def test_stereo(basic_dict_path, stereo_corpus_dir, temp_dir):
temp = os.path.join(temp_dir, 'stereo')
dictionary = Dictionary(basic_dict_path, os.path.join(temp, 'basic'))
dictionary.write()
d = Corpus(stereo_corpus_dir, temp)
d.initialize_corpus(dictionary)
assert (d.get_feat_dim() == '39')
def test_basic(basic_dict_path, basic_corpus_dir, generated_dir):
dictionary = Dictionary(basic_dict_path, os.path.join(generated_dir, 'basic'))
dictionary.write()
output_directory = os.path.join(generated_dir, 'basic')
d = Corpus(basic_corpus_dir, output_directory)
d.initialize_corpus(dictionary)
assert (d.get_feat_dim() == '39')
def test_basic(basic_dict_path, generated_dir):
d = Dictionary(basic_dict_path, os.path.join(generated_dir, 'basic'))
d.write()
assert(set(d.phones) == set(['sil', 'sp','spn', 'phonea','phoneb','phonec']))
assert(set(d.positional_nonsil_phones) == set(['phonea_B','phonea_I','phonea_E', 'phonea_S',
'phoneb_B','phoneb_I','phoneb_E','phoneb_S',
'phonec_B','phonec_I','phonec_E','phonec_S']))
def test_basic(basic_dict_path, generated_dir):
d = Dictionary(basic_dict_path, os.path.join(generated_dir, 'basic'))
d.write()
assert set(d.phones) == {'sil', 'sp', 'spn', 'phonea', 'phoneb', 'phonec'}
assert set(d.positional_nonsil_phones) == {
'phonea_B', 'phonea_I', 'phonea_E', 'phonea_S', 'phoneb_B', 'phoneb_I',
'phoneb_E', 'phoneb_S', 'phonec_B', 'phonec_I', 'phonec_E', 'phonec_S'
}
def test_stereo(basic_dict_path, stereo_corpus_dir, temp_dir):
temp = os.path.join(temp_dir, 'stereo')
dictionary = Dictionary(basic_dict_path, os.path.join(temp, 'basic'))
dictionary.write()
d = Corpus(stereo_corpus_dir, temp)
d.initialize_corpus(dictionary)
fc = FeatureConfig()
fc.generate_features(d)
assert d.get_feat_dim(fc) == 39
def test_basic(basic_dict_path, basic_corpus_dir, generated_dir):
dictionary = Dictionary(basic_dict_path, os.path.join(generated_dir, 'basic'))
dictionary.write()
output_directory = os.path.join(generated_dir, 'basic')
c = Corpus(basic_corpus_dir, output_directory)
c.initialize_corpus(dictionary)
fc = FeatureConfig()
fc.generate_features(c)
assert c.get_feat_dim(fc) == 39
def test_basic(basic_dict_path, basic_dir, generated_dir):
dictionary = Dictionary(basic_dict_path, os.path.join(generated_dir, "basic"))
dictionary.write()
output_directory = os.path.join(generated_dir, "basic")
d = Corpus(basic_dir, output_directory)
d.write()
d.create_mfccs()
d.setup_splits(dictionary)
assert d.get_feat_dim() == "39"
def test_stereo(basic_dict_path, textgrid_directory, generated_dir):
temp = os.path.join(generated_dir, 'stereo')
dictionary = Dictionary(basic_dict_path, os.path.join(temp, 'basic'))
dictionary.write()
d = Corpus(os.path.join(textgrid_directory, 'stereo'), temp)
d.write()
d.create_mfccs()
d.setup_splits(dictionary)
assert (d.get_feat_dim() == '39')
def test_basic(basic_dict_path, basic_corpus_dir, generated_dir):
dictionary = Dictionary(basic_dict_path, os.path.join(generated_dir, 'basic'))
dictionary.write()
output_directory = os.path.join(generated_dir, 'basic')
d = Corpus(basic_corpus_dir, output_directory)
d.initialize_corpus(dictionary)
fc = FeatureConfig()
fc.generate_features(d)
assert d.get_feat_dim(fc) == 39
def test_stereo(basic_dict_path, textgrid_directory, generated_dir):
temp = os.path.join(generated_dir, "stereo")
dictionary = Dictionary(basic_dict_path, os.path.join(temp, "basic"))
dictionary.write()
d = Corpus(os.path.join(textgrid_directory, "stereo"), temp)
d.write()
d.create_mfccs()
d.setup_splits(dictionary)
assert d.get_feat_dim() == "39"
def test_stereo(basic_dict_path, stereo_corpus_dir, temp_dir):
temp = os.path.join(temp_dir, 'stereo')
dictionary = Dictionary(basic_dict_path, os.path.join(temp, 'basic'))
dictionary.write()
d = Corpus(stereo_corpus_dir, temp)
d.initialize_corpus(dictionary)
fc = FeatureConfig()
fc.generate_features(d)
assert d.get_feat_dim(fc) == 39
def test_basic_txt(basic_corpus_txt_dir, basic_dict_path, generated_dir):
dictionary = Dictionary(basic_dict_path, os.path.join(generated_dir, 'basic'))
dictionary.write()
output_directory = os.path.join(generated_dir, 'basic')
c = Corpus(basic_corpus_txt_dir, output_directory)
assert len(c.no_transcription_files) == 0
c.initialize_corpus(dictionary)
fc = FeatureConfig()
fc.generate_features(c)
assert c.get_feat_dim(fc) == 39
def test_basic(basic_dict_path, basic_dir, generated_dir):
dictionary = Dictionary(basic_dict_path,
os.path.join(generated_dir, 'basic'))
dictionary.write()
output_directory = os.path.join(generated_dir, 'basic')
d = Corpus(basic_dir, output_directory)
d.write()
d.create_mfccs()
d.setup_splits(dictionary)
assert (d.get_feat_dim() == '39')
def align_corpus(corpus_dir, dict_path, output_directory, temp_dir,
output_model_path, args):
if temp_dir == '':
temp_dir = TEMP_DIR
else:
temp_dir = os.path.expanduser(temp_dir)
corpus_name = os.path.basename(corpus_dir)
if corpus_name == '':
corpus_dir = os.path.dirname(corpus_dir)
corpus_name = os.path.basename(corpus_dir)
data_directory = os.path.join(temp_dir, corpus_name)
if args.clean:
shutil.rmtree(data_directory, ignore_errors=True)
shutil.rmtree(output_directory, ignore_errors=True)
os.makedirs(data_directory, exist_ok=True)
os.makedirs(output_directory, exist_ok=True)
dictionary = Dictionary(dict_path, data_directory)
dictionary.write()
corpus = Corpus(corpus_dir,
data_directory,
args.speaker_characters,
num_jobs=args.num_jobs)
print(corpus.speaker_utterance_info())
corpus.write()
corpus.create_mfccs()
corpus.setup_splits(dictionary)
utt_oov_path = os.path.join(corpus.split_directory, 'utterance_oovs.txt')
if os.path.exists(utt_oov_path):
shutil.copy(utt_oov_path, output_directory)
oov_path = os.path.join(corpus.split_directory, 'oovs_found.txt')
if os.path.exists(oov_path):
shutil.copy(oov_path, output_directory)
mono_params = {'align_often': not args.fast}
tri_params = {'align_often': not args.fast}
tri_fmllr_params = {'align_often': not args.fast}
a = TrainableAligner(corpus,
dictionary,
output_directory,
temp_directory=data_directory,
mono_params=mono_params,
tri_params=tri_params,
tri_fmllr_params=tri_fmllr_params,
num_jobs=args.num_jobs)
a.verbose = args.verbose
a.train_mono()
a.export_textgrids()
a.train_tri()
a.export_textgrids()
a.train_tri_fmllr()
a.export_textgrids()
if output_model_path is not None:
a.save(output_model_path)
def test_short_segments(basic_dict_path, shortsegments_corpus_dir, temp_dir):
temp = os.path.join(temp_dir, 'short_segments')
dictionary = Dictionary(basic_dict_path, temp)
dictionary.write()
corpus = Corpus(shortsegments_corpus_dir, temp)
corpus.initialize_corpus(dictionary)
assert (len(corpus.feat_mapping.keys()) == 2)
assert (len(corpus.utt_speak_mapping.keys()) == 2)
assert (len(corpus.speak_utt_mapping.keys()) == 1)
assert (len(corpus.text_mapping.keys()) == 2)
assert (len(corpus.utt_wav_mapping.keys()) == 1)
assert (len(corpus.segments.keys()) == 2)
assert (len(corpus.ignored_utterances) == 1)
def test_subset(large_prosodylab_format_directory, temp_dir, large_dataset_dictionary):
output_directory = os.path.join(temp_dir, 'large_subset')
shutil.rmtree(output_directory, ignore_errors=True)
d = Dictionary(large_dataset_dictionary, output_directory)
d.write()
c = Corpus(large_prosodylab_format_directory, output_directory)
c.initialize_corpus(d)
sd = c.split_directory()
fc = FeatureConfig()
fc.generate_features(c)
s = c.subset_directory(10, fc)
assert os.path.exists(sd)
assert os.path.exists(s)
def test_subset(large_prosodylab_format_directory, temp_dir, large_dataset_dictionary):
output_directory = os.path.join(temp_dir, 'large_subset')
shutil.rmtree(output_directory, ignore_errors=True)
d = Dictionary(large_dataset_dictionary, output_directory)
d.write()
c = Corpus(large_prosodylab_format_directory, output_directory)
c.initialize_corpus(d)
sd = c.split_directory()
fc = FeatureConfig()
fc.generate_features(c)
s = c.subset_directory(10, fc)
assert os.path.exists(sd)
assert os.path.exists(s)
def test_short_segments(basic_dict_path, shortsegments_corpus_dir, temp_dir):
temp = os.path.join(temp_dir, 'short_segments')
dictionary = Dictionary(basic_dict_path, temp)
dictionary.write()
corpus = Corpus(shortsegments_corpus_dir, temp)
corpus.initialize_corpus(dictionary)
fc = FeatureConfig()
fc.generate_features(corpus)
assert len(corpus.feat_mapping.keys()) == 2
assert len(corpus.utt_speak_mapping.keys()) == 3
assert len(corpus.speak_utt_mapping.keys()) == 1
assert len(corpus.text_mapping.keys()) == 3
assert len(corpus.utt_wav_mapping.keys()) == 1
assert len(corpus.segments.keys()) == 3
assert len(corpus.ignored_utterances) == 1
def test_basic_noposition(basic_dict_path, generated_dir):
d = Dictionary(basic_dict_path,
os.path.join(generated_dir, 'basic'),
position_dependent_phones=False)
x = d.write()
assert (set(d.phones) == set(
['sil', 'sp', 'spn', 'phonea', 'phoneb', 'phonec']))
def align_corpus(corpus_dir, dict_path, output_directory, temp_dir,
output_model_path, args):
if temp_dir == '':
temp_dir = TEMP_DIR
else:
temp_dir = os.path.expanduser(temp_dir)
corpus_name = os.path.basename(corpus_dir)
if corpus_name == '':
corpus_dir = os.path.dirname(corpus_dir)
corpus_name = os.path.basename(corpus_dir)
data_directory = os.path.join(temp_dir, corpus_name)
if args.clean:
shutil.rmtree(data_directory, ignore_errors = True)
shutil.rmtree(output_directory, ignore_errors = True)
os.makedirs(data_directory, exist_ok = True)
os.makedirs(output_directory, exist_ok = True)
corpus = Corpus(corpus_dir, data_directory, args.speaker_characters, num_jobs = args.num_jobs)
print(corpus.speaker_utterance_info())
corpus.write()
corpus.create_mfccs()
dictionary = Dictionary(dict_path, data_directory, word_set=corpus.word_set)
dictionary.write()
corpus.setup_splits(dictionary)
utt_oov_path = os.path.join(corpus.split_directory, 'utterance_oovs.txt')
if os.path.exists(utt_oov_path):
shutil.copy(utt_oov_path, output_directory)
oov_path = os.path.join(corpus.split_directory, 'oovs_found.txt')
if os.path.exists(oov_path):
shutil.copy(oov_path, output_directory)
mono_params = {'align_often': not args.fast}
tri_params = {'align_often': not args.fast}
tri_fmllr_params = {'align_often': not args.fast}
a = TrainableAligner(corpus, dictionary, output_directory,
temp_directory = data_directory,
mono_params = mono_params, tri_params = tri_params,
tri_fmllr_params = tri_fmllr_params, num_jobs = args.num_jobs)
a.verbose = args.verbose
a.train_mono()
a.export_textgrids()
a.train_tri()
a.export_textgrids()
a.train_tri_fmllr()
a.export_textgrids()
if output_model_path is not None:
a.save(output_model_path)
def test_speaker_groupings(large_prosodylab_format_directory, temp_dir,
large_dataset_dictionary):
output_directory = os.path.join(temp_dir, 'large')
shutil.rmtree(output_directory, ignore_errors=True)
d = Dictionary(large_dataset_dictionary, output_directory)
d.write()
c = Corpus(large_prosodylab_format_directory, output_directory)
c.initialize_corpus(d)
fc = FeatureConfig()
fc.generate_features(c)
speakers = os.listdir(large_prosodylab_format_directory)
for s in speakers:
assert any(s in x for x in c.speaker_groups)
for root, dirs, files in os.walk(large_prosodylab_format_directory):
for f in files:
name, ext = os.path.splitext(f)
assert any(name in x for x in c.groups)
for root, dirs, files in os.walk(large_prosodylab_format_directory):
for f in files:
name, ext = os.path.splitext(f)
assert any(name in x for x in c.feat_mapping)
shutil.rmtree(output_directory, ignore_errors=True)
d.write()
c = Corpus(large_prosodylab_format_directory, output_directory, num_jobs=2)
c.initialize_corpus(d)
fc.generate_features(c)
for s in speakers:
assert any(s in x for x in c.speaker_groups)
for root, dirs, files in os.walk(large_prosodylab_format_directory):
for f in files:
name, ext = os.path.splitext(f)
assert any(name in x for x in c.groups)
for root, dirs, files in os.walk(large_prosodylab_format_directory):
for f in files:
name, ext = os.path.splitext(f)
assert any(name in x for x in c.feat_mapping)
def test_frclitics(frclitics_dict_path, generated_dir):
d = Dictionary(frclitics_dict_path, os.path.join(generated_dir, 'frclitics'))
x = d.write()
assert d.separate_clitics('aujourd') == ['aujourd']
assert d.separate_clitics('aujourd\'hui') == ['aujourd\'hui']
assert d.separate_clitics('vingt-six') == ['vingt', 'six']
assert d.separate_clitics('m\'appelle') == ['m\'', 'appelle']
assert d.separate_clitics('c\'est') == ['c\'est']
assert d.separate_clitics('purple-people-eater') == ['purple-people-eater']
assert d.separate_clitics('m\'appele') == ['m\'', 'appele']
assert d.separate_clitics('m\'ving-sic') == ["m'", 'ving', 'sic']
assert d.separate_clitics('flying\'purple-people-eater') == ['flying\'purple-people-eater']
def test_speaker_groupings(large_prosodylab_format_directory, temp_dir, large_dataset_dictionary):
output_directory = os.path.join(temp_dir, 'large')
shutil.rmtree(output_directory, ignore_errors=True)
d = Dictionary(large_dataset_dictionary, output_directory)
d.write()
c = Corpus(large_prosodylab_format_directory, output_directory)
c.initialize_corpus(d)
fc = FeatureConfig()
fc.generate_features(c)
speakers = os.listdir(large_prosodylab_format_directory)
for s in speakers:
assert any(s in x for x in c.speaker_groups)
for root, dirs, files in os.walk(large_prosodylab_format_directory):
for f in files:
name, ext = os.path.splitext(f)
assert any(name in x for x in c.groups)
for root, dirs, files in os.walk(large_prosodylab_format_directory):
for f in files:
name, ext = os.path.splitext(f)
assert any(name in x for x in c.feat_mapping)
shutil.rmtree(output_directory, ignore_errors=True)
d.write()
c = Corpus(large_prosodylab_format_directory, output_directory, num_jobs=2)
c.initialize_corpus(d)
fc.generate_features(c)
for s in speakers:
assert any(s in x for x in c.speaker_groups)
for root, dirs, files in os.walk(large_prosodylab_format_directory):
for f in files:
name, ext = os.path.splitext(f)
assert any(name in x for x in c.groups)
for root, dirs, files in os.walk(large_prosodylab_format_directory):
for f in files:
name, ext = os.path.splitext(f)
assert any(name in x for x in c.feat_mapping)
def test_frclitics(frclitics_dict_path, generated_dir):
d = Dictionary(frclitics_dict_path, os.path.join(generated_dir,
'frclitics'))
x = d.write()
assert d.separate_clitics('aujourd') == ['aujourd']
assert d.separate_clitics('aujourd\'hui') == ['aujourd\'hui']
assert d.separate_clitics('vingt-six') == ['vingt', 'six']
assert d.separate_clitics('m\'appelle') == ['m\'', 'appelle']
assert d.separate_clitics('c\'est') == ['c\'est']
assert d.separate_clitics('purple-people-eater') == ['purple-people-eater']
assert d.separate_clitics('m\'appele') == ['m\'', 'appele']
assert d.separate_clitics('m\'ving-sic') == ["m'", 'ving', 'sic']
assert d.separate_clitics('flying\'purple-people-eater') == [
'flying\'purple-people-eater'
]
def test_extra_annotations(extra_annotations_path, generated_dir):
d = Dictionary(extra_annotations_path,
os.path.join(generated_dir, 'extra'))
assert ('{' in d.graphemes)
d.write()
def sick_dict(sick_dict_path, generated_dir):
output_directory = os.path.join(generated_dir, 'sickcorpus')
dictionary = Dictionary(sick_dict_path, output_directory)
dictionary.write()
return dictionary
def test_basic_noposition(basic_dict_path, generated_dir):
d = Dictionary(basic_dict_path, os.path.join(generated_dir, 'basic'), position_dependent_phones = False)
x = d.write()
assert(set(d.phones) == set(['sil', 'sp','spn', 'phonea','phoneb','phonec']))
def sick_dict(sick_dict_path, generated_dir):
output_directory = os.path.join(generated_dir, 'sickcorpus')
dictionary = Dictionary(sick_dict_path, output_directory)
dictionary.write()
return dictionary
def test_extra_annotations(extra_annotations_path, generated_dir):
d = Dictionary(extra_annotations_path, os.path.join(generated_dir, 'extra'))
assert('{' in d.graphemes)
d.write()
