def test_pmsqe_pit(n_src, sample_rate): # Define supported STFT if sample_rate == 16000: stft = Encoder(STFTFB(kernel_size=512, n_filters=512, stride=256)) else: stft = Encoder(STFTFB(kernel_size=256, n_filters=256, stride=128)) # Usage by itself ref, est = torch.randn(2, n_src, 16000), torch.randn(2, n_src, 16000) ref_spec = transforms.mag(stft(ref)) est_spec = transforms.mag(stft(est)) loss_func = PITLossWrapper(SingleSrcPMSQE(sample_rate=sample_rate), pit_from="pw_pt") # Assert forward ok. loss_func(est_spec, ref_spec)
def test_pmsqe(sample_rate): # Define supported STFT if sample_rate == 16000: stft = Encoder(STFTFB(kernel_size=512, n_filters=512, stride=256)) else: stft = Encoder(STFTFB(kernel_size=256, n_filters=256, stride=128)) # Usage by itself ref, est = torch.randn(2, 1, 16000), torch.randn(2, 1, 16000) ref_spec = transforms.mag(stft(ref)) est_spec = transforms.mag(stft(est)) loss_func = SingleSrcPMSQE(sample_rate=sample_rate) loss_value = loss_func(est_spec, ref_spec) # Assert output has shape (batch,) assert loss_value.shape[0] == ref.shape[0] # Assert support for transposed inputs. tr_loss_value = loss_func(est_spec.transpose(1, 2), ref_spec.transpose(1, 2)) assert_allclose(loss_value, tr_loss_value)