"--syn_models_dir",
type=Path,
default="synthesizer/saved_models",
help="Directory containing saved synthesizer models")
parser.add_argument("-v",
"--voc_models_dir",
type=Path,
default="vocoder/saved_models",
help="Directory containing saved vocoder models")
parser.add_argument("--cpu", action="store_true", help=\
"If True, processing is done on CPU, even when a GPU is available.")
parser.add_argument("--seed", type=int, default=None, help=\
"Optional random number seed value to make toolbox deterministic.")
parser.add_argument("--no_mp3_support", action="store_true", help=\
"If True, no mp3 files are allowed.")
args = parser.parse_args()
print_args(args, parser)
if args.cpu:
# Hide GPUs from Pytorch to force CPU processing
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
del args.cpu
## Remind the user to download pretrained models if needed
check_model_paths(encoder_path=args.enc_models_dir,
synthesizer_path=args.syn_models_dir,
vocoder_path=args.voc_models_dir)
# Launch the toolbox
Toolbox(**vars(args))
if torch.cuda.is_available():
device_id = torch.cuda.current_device()
gpu_properties = torch.cuda.get_device_properties(device_id)
## Print some environment information (for debugging purposes)
print(
"Found %d GPUs available. Using GPU %d (%s) of compute capability %d.%d with "
"%.1fGb total memory.\n" %
(torch.cuda.device_count(), device_id, gpu_properties.name,
gpu_properties.major, gpu_properties.minor,
gpu_properties.total_memory / 1e9))
else:
print("Using CPU for inference.\n")
## Remind the user to download pretrained models if needed
check_model_paths(encoder_path=args.enc_model_fpath,
synthesizer_path=args.syn_model_fpath,
vocoder_path=args.voc_model_fpath)
## Load the models one by one.
print("Preparing the encoder, the synthesizer and the vocoder...")
encoder.load_model(args.enc_model_fpath)
synthesizer = Synthesizer(args.syn_model_fpath)
vocoder.load_model(args.voc_model_fpath)
## Run a test
print("Testing your configuration with small inputs.")
# Forward an audio waveform of zeroes that lasts 1 second. Notice how we can get the encoder's
# sampling rate, which may differ.
# If you're unfamiliar with digital audio, know that it is encoded as an array of floats
# (or sometimes integers, but mostly floats in this projects) ranging from -1 to 1.
# The sampling rate is the number of values (samples) recorded per second, it is set to
from voices_dict import voices_dict
Lorem_Ipsum = "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua."
encoder_path = Path(
"/Users/glw001/Documents/Development/voice_clone/Real-Time-Voice-Cloning/encoder/saved_models/pretrained.pt"
)
synthesizer_path = Path(
"/Users/glw001/Documents/Development/voice_clone/Real-Time-Voice-Cloning/synthesizer/saved_models/logs-pretrained/"
)
vocoder_path = Path(
"/Users/glw001/Documents/Development/voice_clone/Real-Time-Voice-Cloning/vocoder/saved_models/pretrained/pretrained.pt"
)
check_model_paths(encoder_path=encoder_path,
synthesizer_path=synthesizer_path,
vocoder_path=vocoder_path)
global in_fpath, filenum, preprocessed_wav, embed, torch, vocoder
filenum = 0
data_path = '/Users/glw001/Documents/Development/voice_clone/LibriSpeech/train-clean-100'
in_fpath = Path(f'{data_path}/F1088-Christabel/134315/1088-134315-0002.flac')
seed = 694201312
word_substitutions = {'do': 'doo', 'Do': 'Doo', 'NPC': 'En Pee See'}
## Load the models one by one.
print("Preparing the encoder, the synthesizer and the vocoder...")
encoder.load_model(encoder_path)