def dataset_modification(config_path, output_path):
data_config_path = '{}/data.yaml'.format(config_path)
data = Utility.yaml_load(data_config_path)
dataset = data['subset']
print dataset
for i in xrange(5, 20, 4):
if training_set[i-1] == 'i':
continue
subset = training_set[0:i]
# print subset
# print len(subset), len(subset)*50
dataset[ '{}-{}'.format(subset[0], subset[len(subset)-1]) ] = subset
# print dataset
# print data
Utility.yaml_save('{}/data.yaml'.format(output_path), data)
pass
def get_context_list_of_a_phone(filepath, target_phone):
yaml_file = Utility.yaml_load(filepath)
# print yaml_file['preprocess']
print 'Target phone : {}'.format(target_phone)
for event in yaml_file['context_events']:
name = event['name']
args = event['value_getter']['event_feature']['args']
type = None
if len(args) > 1:
type = args[1]['args'][0]
# print type
if type == 'entity':
d = "{}".format(args[0])
d = d.split(',')
for ph in d:
if '\'{}\''.format(target_phone) in ph:
ph = '{}'.format(ph)
ph = ph.split('[')[-1].split(']')[0]
# print ph
# if int(ph) == 1:
if 'begin' in name:
if ph == '{}'.format(1):
print name, ph
# print d
# break
# Utility.print_yaml_formatted(yaml_file['context_events'][2])
# Utility.print_yaml_formatted(yaml_file['context_events'][2]['name'])
# Utility.print_yaml_formatted(yaml_file['context_events'][2]['value_getter']['event_feature']['args'][0]['uua'])
pass
def change_exp(config_path, output_path, subset):
exp = Utility.yaml_load( '{}/experiment.yaml'.format(config_path) )
exp['data_set']['optim_dur'] = 'a-{}'.format(subset[len(subset)-1])
exp['data_set']['train'] = 'a-{}'.format(subset[len(subset)-1])
print exp
Utility.yaml_save('{}/experiment.yaml'.format(output_path), exp)
pass
def run_gen_mono(utt_set):
set_path = '{}/{}/'.format(utterance_path, utt_set)
set_syllable_base_path = '{}/{}/'.format(syllable_base, utt_set)
out_set_path = '{}/{}/'.format(output_path, utt_set)
Utility.make_directory(out_set_path)
for i in xrange(1, 51):
utt_file = Utility.yaml_load('{}/tscsd{}{}.utt.yaml'.format(
set_path, utt_set, Utility.fill_zero(i, 2)))
# print utt_file
out_file = '{}/tscsd{}{}.lab'.format(out_set_path, utt_set,
Utility.fill_zero(i, 2))
stress_list = []
recursion(utt_file, stress_list)
syllable_time_label = Utility.read_file_line_by_line(
'{}/tscsd{}{}.lab'.format(set_syllable_base_path, utt_set,
Utility.fill_zero(i, 2)))
# print stress_list, len(stress_list)
# print len(syllable_time_label)
if len(syllable_time_label) != len(stress_list):
print utt_set, i
# print 'Error'
# sys.exit()
out = []
for idx, line in enumerate(syllable_time_label):
# print line, stress_list[idx]
o = '{}::{}'.format(
Utility.trim(line).replace('-', '_').replace('+', '_'),
stress_list[idx])
# print o
out.append(o)
Utility.write_to_file_line_by_line(out_file, out)
# sys.exit()
pass
Utility.make_directory(set_out_path)
if Utility.is_dir_exists(set_stress_path) & Utility.is_dir_exists(set_utt_base_path):
print ch
for i in xrange(1, 51):
name = 'tscsd{}{}'.format(ch, Utility.fill_zero(i, 2))
yaml_filename = '{}/{}.utt.yaml'.format(set_utt_base_path, name )
if not Utility.is_file_exist(yaml_filename):
continue
full_file = '{}/{}.lab'.format(set_syllable_full_path, name)
count = [0]
yaml = Utility.yaml_load(yaml_filename)
add_stress(yaml, count, name)
if not (len(Utility.read_file_line_by_line(full_file)) == count[0] ):
print 'Not equal'
print name, len(Utility.read_file_line_by_line(full_file)), count[0]
out_file = '{}/{}.utt.yaml'.format(set_out_path, name)
Utility.yaml_save(out_file, yaml)
print 'all no {} names '.format(coun_no)
pass
def get_syllable_list_from_syl_based_utterance_object(utt, syl_list=[]):
for u in utt:
# print u
if u['unit'] == 'syllable':
syl = '{}-{}-{}-{}'.format(u['consonant'], u['vowel'],
u['final_consonant'], u['tone_type'])
syl_list.append(syl)
else:
get_syllable_list_from_syl_based_utterance_object(
u['inners'], syl_list=syl_list)
pass
if __name__ == '__main__':
utt_path = '/home/h1/decha/Dropbox/Inter_speech_2016/Training_data/03_GPR_syllable_level/utt/tsc/sd/a/tscsda01.utt.yaml'
utt = Utility.yaml_load(utt_path)
syl_list = []
get_syllable_list_from_syl_based_utterance_object(utt, syl_list=syl_list)
print syl_list
# Utility.print_yaml_formatted(utt)
pass
