def test_pqmf():
w, sr = load(WAV_FILE)
layer = PQMF(N=4, taps=62, cutoff=0.15, beta=9.0)
w, sr = load(WAV_FILE)
w2 = torch.from_numpy(w[None, None, :])
b2 = layer.analysis(w2)
w2_ = layer.synthesis(b2)
print(w2_.max())
print(w2_.min())
print(w2_.mean())
sf.write('pqmf_output.wav', w2_.flatten().detach(), sr)
def __init__(self,
in_channels=80,
out_channels=4,
proj_kernel=7,
base_channels=384,
upsample_factors=(2, 8, 2, 2),
res_kernel=3,
num_res_blocks=3):
super(MultibandMelganGenerator,
self).__init__(in_channels=in_channels,
out_channels=out_channels,
proj_kernel=proj_kernel,
base_channels=base_channels,
upsample_factors=upsample_factors,
res_kernel=res_kernel,
num_res_blocks=num_res_blocks)
self.pqmf_layer = PQMF(N=4, taps=62, cutoff=0.15, beta=9.0)