Fixes

Author: Alejandro Gaston Alvarez Franceschi

coremltools/converters/mil/frontend/torch/test/test_torch_ops.py

@@ -9548,7 +9548,7 @@ def test_istft(self, compute_unit, backend, channels, n_fft, num_frames, hop_len
         if return_complex and onesided:
             pytest.skip("Complex output is incompatible with onesided")
 
-        freq = n_fft*2+1 if onesided else n_fft
+        freq = n_fft//2+1 if onesided else n_fft
         input_shape = (channels, freq, num_frames) if channels else (freq, num_frames)
 
         class ISTFTModel(torch.nn.Module):
@@ -9569,12 +9569,34 @@ def forward(self, x):
                     x = torch.stack([torch.real(x), torch.imag(x)], dim=0)
                 return x
 
-        TorchBaseTest.run_compare_torch(
-            input_shape,
-            ISTFTModel(),
-            backend=backend,
-            compute_unit=compute_unit
-        )
+        if length is not None or center is False:
+            # For some reason Pytorch raises an error https://github.com/pytorch/audio/issues/427#issuecomment-1829593033
+            with pytest.raises(
+                RuntimeError, match="istft\(.*\) window overlap add min: 1"
+            ):
+                TorchBaseTest.run_compare_torch(
+                    input_shape,
+                    ISTFTModel(),
+                    backend=backend,
+                    compute_unit=compute_unit
+                )
+        elif return_complex is False:
+            with pytest.raises(
+                ValueError, match="MIL doesn't support complex data as model's output"
+            ):
+                TorchBaseTest.run_compare_torch(
+                    input_shape,
+                    ISTFTModel(),
+                    backend=backend,
+                    compute_unit=compute_unit
+                )
+        else:
+            TorchBaseTest.run_compare_torch(
+                input_shape,
+                ISTFTModel(),
+                backend=backend,
+                compute_unit=compute_unit
+            )
 
 if _HAS_TORCH_AUDIO:
 

coremltools/converters/mil/mil/passes/defs/lower_complex_dialect_ops.py

@@ -486,12 +486,12 @@ def _istft(
     if length is not None:
         if length.val > expected_output_signal_len:
             if channels:
-                right_pad = mb.fill(shape=(channels, expected_output_signal_len - length), value=0., before_op=before_op)
+                right_pad = mb.fill(shape=(channels, length.val - expected_output_signal_len ), value=0., before_op=before_op)
             else:
-                right_pad = mb.fill(shape=(expected_output_signal_len - length,), value=0., before_op=before_op)
+                right_pad = mb.fill(shape=(length.val - expected_output_signal_len,), value=0., before_op=before_op)
 
-            real_result = mb.stack(x=(real_result, right_pad), axis=1, before_op=before_op)
-            imag_result = mb.stack(x=(imag_result, right_pad), axis=1, before_op=before_op)
+            real_result = mb.stack(values=(real_result, right_pad), axis=1, before_op=before_op)
+            imag_result = mb.stack(values=(imag_result, right_pad), axis=1, before_op=before_op)
         elif length.val < expected_output_signal_len:
             real_result = mb.slice_by_size(x=real_result, begin=[0], size=[length.val], before_op=before_op)
             imag_result = mb.slice_by_size(x=imag_result, begin=[0], size=[length.val], before_op=before_op)