def prepare(args):
idim = 10
odim = len(args.char_list)
model = E2E(idim, odim, args)
batchsize = 2
x = torch.randn(batchsize, 15, idim)
ilens = [15, 10]
n_token = odim - 2 # w/o <eos>/<sos>, <mask>
y = (torch.rand(batchsize, 10) * n_token % n_token).long()
olens = [7, 6]
for i in range(batchsize):
x[i, ilens[i]:] = -1
y[i, olens[i]:] = model.ignore_id
data = []
for i in range(batchsize):
data.append((
"utt%d" % i,
{
"input": [{
"shape": [ilens[i], idim]
}],
"output": [{
"shape": [olens[i]]
}],
},
))
return model, x, torch.tensor(ilens), y, data
def add_arguments(parser):
"""Add arguments."""
E2ETransformer.add_arguments(parser)
E2E.add_conformer_arguments(parser)
return parser
def add_arguments(parser):
"""Add arguments."""
E2EASR.add_arguments(parser)
E2EASRMIX.encoder_mix_add_arguments(parser)
return parser
def add_arguments(parser):
"""Add arguments."""
E2ETransformer.add_arguments(parser)
E2E.add_maskctc_arguments(parser)
return parser
def add_arguments(parser):
"""Add arguments."""
E2ETransformer.add_arguments(parser)
E2E.add_hopfield_arguments(parser)
return parser