def version_compare(version1, version2):
version1 = version1.split(".")
version2 = version2.split(".")
num = min(len(version1), len(version2))
for index in range(num):
try:
vn1 = int(version1[index])
except:
vn1 = 0
try:
vn2 = int(version2[index])
except:
vn2 = 0
if vn1 > vn2:
return True
elif vn1 < vn2:
return False
return len(version1) > len(version2)
if version_compare(paddle.__version__, "1.8.0"):
print("verison greater than 1.8")
import paddle.fluid as fluid
else:
print("verison is: %s" % paddle.__version__)
import paddle.fluid.dygraph as dygraph
dygraph.enable_dygraph()
help="path to save synthesized audio")
args = parser.parse_args()
with open(args.config, 'rt') as f:
config = ruamel.yaml.safe_load(f)
print("Command Line Args: ")
for k, v in vars(args).items():
print("{}: {}".format(k, v))
if args.device == -1:
place = fluid.CPUPlace()
else:
place = fluid.CUDAPlace(args.device)
dg.enable_dygraph(place)
model = make_model(config)
checkpoint_dir = os.path.join(args.output, "checkpoints")
if args.checkpoint is not None:
iteration = io.load_parameters(model, checkpoint_path=args.checkpoint)
else:
iteration = io.load_parameters(model,
checkpoint_dir=checkpoint_dir,
iteration=args.iteration)
# WARNING: don't forget to remove weight norm to re-compute each wrapped layer's weight
# removing weight norm also speeds up computation
for layer in model.sublayers():
if isinstance(layer, WeightNormWrapper):
layer.remove_weight_norm()
parser.add_argument("--config",
type=str,
required=True,
help="config file")
parser.add_argument("--input",
type=str,
required=True,
help="text file to synthesize")
parser.add_argument("--output",
type=str,
required=True,
help="path to save audio")
parser.add_argument("--checkpoint",
type=str,
required=True,
help="data path of the checkpoint")
parser.add_argument("--monotonic_layers",
type=str,
required=True,
help="monotonic decoder layers' indices(start from 1)")
parser.add_argument("--vocoder",
type=str,
default="waveflow",
choices=['griffin-lim', 'waveflow'],
help="vocoder to use")
args = parser.parse_args()
with open(args.config, 'rt') as f:
config = yaml.safe_load(f)
dg.enable_dygraph(fluid.CUDAPlace(0))
main(args, config)
parser.add_argument("--input",
type=str,
required=True,
help="data path of the original data")
args = parser.parse_args()
with open(args.config, 'rt') as f:
config = yaml.safe_load(f)
print("========= Command Line Arguments ========")
for k, v in vars(args).items():
print("{}: {}".format(k, v))
print("=========== Configurations ==============")
for k in ["p_pronunciation", "batch_size"]:
print("{}: {}".format(k, config[k]))
ljspeech = LJSpeech(args.input)
collate_fn = DataCollector(config["p_pronunciation"])
dg.enable_dygraph(fluid.CPUPlace())
sampler = PartialyRandomizedSimilarTimeLengthSampler(ljspeech.num_frames())
cargo = DataCargo(ljspeech,
collate_fn,
batch_size=config["batch_size"],
sampler=sampler)
loader = DataLoader\
.from_generator(capacity=5, return_list=True)\
.set_batch_generator(cargo)
for i, batch in tqdm.tqdm(enumerate(loader)):
continue