def benchmark_align_corpus(corpus_dir, dict_path, output_directory, speaker_characters, fast,
output_model_path, num_jobs, verbose):
beg = time.time()
align_corpus(corpus_dir, dict_path, output_directory, speaker_characters, fast,
output_model_path, num_jobs, verbose, False)
end = time.time()
return [(end - beg)]
def benchmark_align_corpus(corpus_dir, dict_path, output_directory,
speaker_characters, fast, output_model_path,
num_jobs, verbose):
beg = time.time()
align_corpus(corpus_dir, dict_path, output_directory, speaker_characters,
fast, output_model_path, num_jobs, verbose, False)
end = time.time()
return [(end - beg)]
def benchmark_align_corpus():
beg = time.time()
align_corpus(corpus_dir, dict_path, output_directory, temp_dir, model_path, args)
end = time.time()
dict_data = {'Computer': platform.node(),
'Date': str(datetime.now()),
'Corpus': corpus_dir,
'Type of benchmark': 'align english',
'Total time': end - beg,
'Num_jobs': args.num_jobs}
return dict_data
self.verbose = False
self.clean = True
self.no_speaker_adaptation = False
self.temp_directory = '/data/mmcauliffe/temp/MFA'
args = DummyArgs()
args.corpus_directory = '/media/share/datasets/aligner_benchmarks/sorted_quebec_french'
args.dictionary_path = '/media/share/corpora/GP_for_MFA/FR/dict/fr.dict'
args.output_directory = '/data/mmcauliffe/aligner-output/aligned_quebec_french'
args.output_model_path = '/data/mmcauliffe/aligner-models/french_qc.zip'
if not os.path.exists(args.output_model_path):
fix_path()
try:
beg = time.time()
align_corpus(args)
end = time.time()
duration = end - beg
except Exception as e:
exc_type, exc_value, exc_traceback = sys.exc_info()
print('{} encountered an error!'.format(full_name))
traceback.print_exception(exc_type, exc_value, exc_traceback,
file=sys.stdout)
unfix_path()
csv_columns = ['Computer','Date','Corpus', 'Version', 'Language', 'Type of benchmark', 'Total time', 'Num_jobs']
now = datetime.now()
date = str(now.year)+str(now.month)+str(now.day)
dict_data = {'Computer': platform.node(),
def benchmark_align_corpus():
beg = time.time()
align_corpus(corpus_dir, dict_path, output_directory, temp_dir,
output_model_path, args)
end = time.time()
return [(end - beg)]
self.clean = True
self.no_speaker_adaptation = False
self.temp_directory = '/data/mmcauliffe/temp/MFA'
args = DummyArgs()
args.corpus_directory = '/media/share/datasets/aligner_benchmarks/sorted_quebec_french'
args.dictionary_path = '/media/share/corpora/GP_for_MFA/FR/dict/fr.dict'
args.output_directory = '/data/mmcauliffe/aligner-output/aligned_quebec_french'
args.output_model_path = '/data/mmcauliffe/aligner-models/french_qc.zip'
if not os.path.exists(args.output_model_path):
fix_path()
try:
beg = time.time()
align_corpus(args)
end = time.time()
duration = end - beg
except Exception as e:
exc_type, exc_value, exc_traceback = sys.exc_info()
print('{} encountered an error!'.format(full_name))
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
file=sys.stdout)
unfix_path()
csv_columns = [
'Computer', 'Date', 'Corpus', 'Version', 'Language', 'Type of benchmark',
'Total time', 'Num_jobs'
]
def align_gp(lang_code, full_name):
if lang_code == 'FR':
args = DummyArgs()
args.corpus_directory = '/media/share/corpora/GP_for_MFA/{}'.format(lang_code)
args.dictionary_path = '/media/share/corpora/GP_for_MFA/{0}/dict/fr.dict'.format(lang_code)
args.output_directory = '/data/mmcauliffe/aligner-output/{}'.format(lang_code)
args.output_model_path = '/data/mmcauliffe/aligner-models/{}_prosodylab.zip'.format(full_name)
if not os.path.exists(args.output_model_path):
try:
align_corpus(args)
except Exception as e:
exc_type, exc_value, exc_traceback = sys.exc_info()
print('{} encountered an error!'.format(full_name))
traceback.print_exception(exc_type, exc_value, exc_traceback,
file=sys.stdout)
args = DummyArgs()
args.corpus_directory = '/media/share/corpora/GP_for_MFA/{}'.format(lang_code)
args.dictionary_path = '/media/share/corpora/GP_for_MFA/{0}/dict/lexique.dict'.format(lang_code)
args.output_directory = '/data/mmcauliffe/aligner-output/{}'.format(lang_code)
args.output_model_path = '/data/mmcauliffe/aligner-models/{}_lexique.zip'.format(full_name)
if not os.path.exists(args.output_model_path):
try:
align_corpus(args)
except Exception as e:
exc_type, exc_value, exc_traceback = sys.exc_info()
print('{} encountered an error!'.format(full_name))
traceback.print_exception(exc_type, exc_value, exc_traceback,
file=sys.stdout)
elif lang_code == 'GE':
args = DummyArgs()
args.corpus_directory = '/media/share/corpora/GP_for_MFA/{}'.format(lang_code)
args.dictionary_path = '/media/share/corpora/GP_for_MFA/{0}/dict/de.dict'.format(lang_code)
args.output_directory = '/data/mmcauliffe/aligner-output/{}'.format(lang_code)
args.output_model_path = '/data/mmcauliffe/aligner-models/{}_prosodylab.zip'.format(full_name)
if not os.path.exists(args.output_model_path):
try:
align_corpus(args)
except Exception as e:
exc_type, exc_value, exc_traceback = sys.exc_info()
print('{} encountered an error!'.format(full_name))
traceback.print_exception(exc_type, exc_value, exc_traceback,
file=sys.stdout)
args = DummyArgs()
args.corpus_directory = '/media/share/corpora/GP_for_MFA/{}'.format(lang_code)
args.dictionary_path = '/media/share/corpora/GP_for_MFA/{0}/dict/{0}_dictionary.txt'.format(lang_code)
args.output_directory = '/data/mmcauliffe/aligner-output/{}'.format(lang_code)
args.output_model_path = '/data/mmcauliffe/aligner-models/{}.zip'.format(full_name)
if os.path.exists(args.output_model_path):
print('skipping {}, output model already exists'.format(full_name))
return
try:
beg = time.time()
align_corpus(args)
end = time.time()
duration = end - beg
except Exception as e:
exc_type, exc_value, exc_traceback = sys.exc_info()
print('{} encountered an error!'.format(full_name))
traceback.print_exception(exc_type, exc_value, exc_traceback,
file=sys.stdout)
return
csv_columns = ['Computer','Date','Corpus', 'Version', 'Language', 'Type of benchmark', 'Total time', 'Num_jobs']
now = datetime.now()
date = str(now.year)+str(now.month)+str(now.day)
dict_data = {'Computer': platform.node(),
'Date': date,
'Corpus': args.corpus_directory,
'Version': aligner.__version__,
'Language': lang_code,
'Type of benchmark': 'train and align',
'Total time': duration,
'Num_jobs': args.num_jobs}
if not os.path.exists(csv_path):
with open(csv_path, 'a') as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=csv_columns)
writer.writeheader()
with open(csv_path, 'a') as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=csv_columns)
writer.writerow(dict_data)
def benchmark_align_corpus():
beg = time.time()
align_corpus(corpus_dir, dict_path, output_directory, temp_dir, output_model_path, args)
end = time.time()
return [(end - beg)]