def one_vs_one(source, target):
# Print log
logging.debug('Converting audio %s to target %s', source, target)
# Create output path
source_file_name = source.split('/')
source_file_name = source_file_name[len(source_file_name) - 1]
source_file_name = source_file_name.split(".")[0]
str_path = source_file_name + "_to_t" + target + ".wav"
#f'{source_file_name}_to_t{target}.wav'
output_path = os.path.join(conversions_dir, str_path)
# Get features and variables to perform the conversion
_, spec = get_spectrograms(source)
spec_expand = np.expand_dims(spec, axis=0)
spec_tensor = torch.from_numpy(spec_expand).type(torch.FloatTensor)
c = Variable(torch.from_numpy(np.array([int(target)]))).cuda()
# Convert audio to target speaker
result = solver.test_step(spec_tensor, c, gen=args.use_gen)
result = result.squeeze(axis=0).transpose((1, 0))
# Generate and save converted audio
wav_data = spectrogram2wav(result)
write(output_path, rate=args.sample_rate, data=wav_data)
parser.add_argument('-hps',
help='The path of hyper-parameter set',
default='vctk.json')
parser.add_argument('-model', '-m', help='The path of model checkpoint')
parser.add_argument('-source', '-s', help='The path of source .wav file')
parser.add_argument(
'-target',
'-t',
help=
'Target speaker id (integer). Same order as the speaker list when preprocessing (en_speaker_used.txt)'
)
parser.add_argument('-output', '-o', help='output .wav path')
parser.add_argument('-sample_rate', '-sr', default=16000, type=int)
parser.add_argument('--use_gen', default=True, action='store_true')
args = parser.parse_args()
hps = Hps()
hps.load(args.hps)
hps_tuple = hps.get_tuple()
solver = Solver(hps_tuple, None)
solver.load_model(args.model)
_, spec = get_spectrograms(args.source)
spec_expand = np.expand_dims(spec, axis=0)
spec_tensor = torch.from_numpy(spec_expand).type(torch.FloatTensor)
c = Variable(torch.from_numpy(np.array([int(args.target)]))).cuda()
result = solver.test_step(spec_tensor, c, gen=args.use_gen)
result = result.squeeze(axis=0).transpose((1, 0))
wav_data = spectrogram2wav(result)
write(args.output, rate=args.sample_rate, data=wav_data)
def sp2wav(sp):
#exp_sp = np.exp(sp)
exp_sp = sp
wav_data = spectrogram2wav(exp_sp)
return wav_data
def sp2wav(sp): exp_sp = sp wav_data = spectrogram2wav(exp_sp) return wav_data