# create logger
logger = Logger(LOG_DIR)
kwargs = {'num_workers': 0, 'pin_memory': True} if args.cuda else {}
l2_dist = PairwiseDistance(2)
# voxceleb = read_my_voxceleb_structure(args.dataroot)
# if args.makemfb:
#pbar = tqdm(voxceleb)
# for datum in voxceleb:
# # print(datum['filename'])
# mk_MFB((args.dataroot +'/voxceleb1_wav/' + datum['filename']+'.wav'))
# print("Complete convert")
if args.mfb:
transform = transforms.Compose([truncatedinputfromMFB(), totensor()])
transform_T = transforms.Compose([
truncatedinputfromMFB(input_per_file=args.test_input_per_file),
totensor()
])
file_loader = read_MFB
else:
transform = transforms.Compose([
truncatedinput(),
toMFB(),
totensor(),
#tonormal()
])
file_loader = read_audio
# voxceleb_dev = [datum for datum in voxceleb if datum['subset']=='dev']
if args.makemfb:
#pbar = tqdm(voxceleb)
for datum in audio_set:
# print(datum['filename'])
mk_MFB((datum['filename']+'.wav'))
print("Complete convert")
if args.mfb:
transform = transforms.Compose([
concateinputfromMFB(),
to4tensor()
# truncatedinputfromMFB(),
# totensor()
])
transform_T = transforms.Compose([
truncatedinputfromMFB(input_per_file=args.test_input_per_file),
totensor()
])
file_loader = read_MFB
else:
transform = transforms.Compose([
truncatedinput(),
toMFB(),
totensor(),
#tonormal()
])
file_loader = read_audio
enroll_dir = DeepSpeakerEnrollDataset(audio_set=audio_set, dir=args.dataroot, loader=file_loader, transform=transform, enroll=args.enroll)
classes_to_label = enroll_dir.class_to_idx