if args.wav_scp is None and args.feat_scp is None:
logger.info('fallback ... read feat_scp from data_cfg')
args.feat_scp = data_cfg['feat']['all']
if args.mode == 'tf':
assert args.data_cfg is not None
text_iterator = TextIterator(path=data_cfg['text']['all'],
map_text2idx=map_text2idx)
if args.wav_scp is not None:
# list all wav files #
list_key_wav = regex_key_val.findall(open(args.wav_scp).read())
if args.set is not None:
if os.path.exists(args.set):
list_key_wav = DataLoader._subset_data(
list_key_wav, DataLoader._read_key(args.set))
else:
args.set = args.set.split(' ')
list_key_wav = DataLoader._subset_data(list_key_wav, args.set)
list_key_wav = sorted(list_key_wav, key=lambda x: x[0])
# lazy load -- saving memory #
def lazy_generate_feat(path, cfg):
_feat = generate_feat_opts(path=path, cfg=cfg)
if scaler is not None:
_feat = scaler.transform(_feat)
return _feat
list_feat = []
list_feat_len = []
list_key = [x[0] for x in list_key_wav]
import argparse
from utilbox.regex_util import regex_key_val
from euterpe.common.loader import DataLoader
def parse():
parser = argparse.ArgumentParser()
parser.add_argument('--kv', type=str)
parser.add_argument('--set', type=str)
return parser.parse_args()
pass
if __name__ == '__main__':
args = parse()
list_kv = DataLoader._read_key_val(args.kv)
list_set = DataLoader._read_key(args.set)
list_subset = DataLoader._subset_data(list_kv, list_set)
for k, v in list_subset:
print('{} {}'.format(k, v))
pass
if __name__ == '__main__':
args = parse()
args.config = os.path.splitext(args.model)[0] + '.cfg'
data_cfg = yaml.load(open(args.data_cfg))
# construct all subset feat & feat_len
if os.path.exists(args.key):
_key = DataLoader._read_key(args.key)
else:
_key = args.key.split()
_feat_all = DataLoader._read_key_val(data_cfg['feat']['all'])
_feat_len_all_path = '{}_len{}'.format(
*os.path.splitext(data_cfg['feat']['all']))
_feat_len_all = DataLoader._read_key_val(_feat_len_all_path)
_feat_kv = DataLoader._subset_data(_feat_all, _key)
_feat_len_kv = DataLoader._subset_data(_feat_len_all, _key)
model = ModelSerializer.load_config(args.config)
model.load_state_dict(torch.load(args.model))
model.eval() # set as eval mode
if args.gpu >= 0:
torch.cuda.set_device(args.gpu)
torch.cuda.manual_seed(123)
model.cuda(args.gpu)
# get feature and information
data_info = pd.read_csv(data_cfg['misc']['info'], sep=',')
map_key2spk = dict(
(str(k), str(v))