def test_acoustic(basic_corpus_dir, generated_dir):
output_directory = os.path.join(generated_dir, 'acoustic')
d = Corpus(basic_corpus_dir, output_directory)
n = no_dictionary(d, output_directory)
d.initialize_corpus(n)
assert n.words['should'][0][0] == ('s', 'h', 'o', 'u', 'l', 'd')
assert '<vocnoise>' not in n.words
assert n.words['here\'s'][0][0] == ('h', 'e', 'r', 'e', 's')
def test_vietnamese(vietnamese_corpus_dir, temp_dir):
output_directory = os.path.join(temp_dir, 'vietnamese')
d = Corpus(vietnamese_corpus_dir, output_directory)
n = no_dictionary(d, output_directory)
d.initialize_corpus(n)
assert n.words['chăn'][0][0] == ('c', 'h', 'ă', 'n')
assert '<vocnoise>' not in n.words
assert n.words['tập'][0][0] == ('t', 'ậ', 'p')
def test_acoustic(basic_dir, generated_dir):
output_directory = os.path.join(generated_dir, 'acoustic')
d = Corpus(basic_dir, output_directory)
d.write()
d.create_mfccs()
n = no_dictionary(d, output_directory)
d.setup_splits(n)
assert n.words['should'] == [['s', 'h', 'o', 'u', 'l', 'd']]
assert '<vocnoise>' not in n.words
assert n.words['here\'s'] == [['h', 'e', 'r', 'e', 's']]
def test_vietnamese(textgrid_directory, generated_dir):
output_directory = os.path.join(generated_dir, 'vietnamese')
d = Corpus(os.path.join(textgrid_directory, 'vietnamese'), output_directory)
d.write()
d.create_mfccs()
n = no_dictionary(d, output_directory)
d.setup_splits(n)
assert n.words['chăn'] == [['c', 'h', 'ă', 'n']]
assert '<vocnoise>' not in n.words
assert n.words['tập'] == [['t','ậ','p']]
def align_corpus_no_dict(args):
if not args.temp_directory:
temp_dir = TEMP_DIR
else:
temp_dir = os.path.expanduser(args.temp_directory)
corpus_name = os.path.basename(args.corpus_directory)
data_directory = os.path.join(temp_dir, corpus_name)
if args.clean:
shutil.rmtree(data_directory, ignore_errors=True)
shutil.rmtree(args.output_directory, ignore_errors=True)
os.makedirs(data_directory, exist_ok=True)
os.makedirs(args.output_directory, exist_ok=True)
corpus = Corpus(args.corpus_directory,
data_directory,
args.speaker_characters,
num_jobs=getattr(args, 'num_jobs', 3),
debug=getattr(args, 'debug', False),
ignore_exceptions=getattr(args, 'ignore_exceptions',
False))
print(corpus.speaker_utterance_info())
dictionary = no_dictionary(corpus, data_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,
args.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,
debug=args.debug,
skip_input=getattr(args, 'quiet', False))
a.verbose = args.verbose
a.train_mono()
a.export_textgrids()
a.train_tri()
a.export_textgrids()
a.train_tri_fmllr()
a.export_textgrids()
if args.output_model_path is not None:
a.save(args.output_model_path)
def align_corpus_no_dict(corpus_dir, 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)
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())
dictionary = no_dictionary(corpus, data_directory)
dictionary.write()
corpus.write()
corpus.create_mfccs()
corpus.setup_splits(dictionary)
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 align_corpus_no_dict(corpus_dir, output_directory, temp_dir,
output_model_path, args):
if not temp_dir:
temp_dir = TEMP_DIR
else:
temp_dir = os.path.expanduser(temp_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())
dictionary = no_dictionary(corpus, data_directory)
dictionary.write()
corpus.write()
corpus.create_mfccs()
corpus.setup_splits(dictionary)
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)
