dtype Error on torchaudio.transforms.MVDR

[CaA23187]

🐛 Describe the bug

the return of torchaudio.transforms.MVDR.forward() should be return specgram_enhanced.to(dtype) rather than return specgram_enhanced, which mght cause dtype inconsistency between input and output when the dtype of input specgram is complex64

Versions

PyTorch version: 1.11.0+cu102
Is debug build: False
CUDA used to build PyTorch: 10.2
ROCM used to build PyTorch: N/A

OS: Ubuntu 20.04.4 LTS (x86_64)
GCC version: (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0
Clang version: Could not collect
CMake version: version 3.22.2
Libc version: glibc-2.31

Python version: 3.9.7 (default, Sep 16 2021, 13:09:58) [GCC 7.5.0] (64-bit runtime)
Python platform: Linux-5.13.0-30-generic-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 10.1.243
GPU models and configuration:
GPU 0: NVIDIA GeForce RTX 2080 Ti
GPU 1: NVIDIA GeForce RTX 2080 Ti
GPU 2: NVIDIA GeForce RTX 2080 Ti
GPU 3: NVIDIA GeForce RTX 2080 Ti

Nvidia driver version: 510.47.03
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

Versions of relevant libraries:
[pip3] mypy-extensions==0.4.3
[pip3] numpy==1.22.3
[pip3] numpydoc==1.1.0
[pip3] torch==1.11.0
[pip3] torch-tb-profiler==0.3.1
[pip3] torchaudio==0.11.0
[pip3] torchvision==0.12.0
[conda] blas 1.0 mkl
[conda] mkl 2021.4.0 h06a4308_640
[conda] mkl-service 2.4.0 py39h7f8727e_0
[conda] mkl_fft 1.3.1 py39hd3c417c_0
[conda] mkl_random 1.2.2 py39h51133e4_0
[conda] mypy_extensions 0.4.3 py39h06a4308_0
[conda] numpy 1.22.3 pypi_0 pypi
[conda] numpydoc 1.1.0 pyhd3eb1b0_1
[conda] torch 1.11.0 pypi_0 pypi
[conda] torch-tb-profiler 0.3.1 pypi_0 pypi
[conda] torchaudio 0.11.0 pypi_0 pypi
[conda] torchvision 0.12.0 pypi_0 pypi

[nateanl]

Hi @CaA23187, thanks for pointing it out. You are right, the line in the forward method should be specgram_enhanced = specgram_enhanced.to(dtype). I will fix it now. Thanks!

[nateanl]

Hi @CaA23187, the dtype error is fixed in #2376. Feel free to create an issue when you meet other errors or have questions on the multi-channel modules, and thanks for helping improve the usability of torchaudio.