[0.6341, 0.4901, 0.8964, 0.4556, 0.6323]])
Breaking Changes
- Removed `Compose`:
Please use core abstractions such as [nn.Sequential()](https://pytorch.org/docs/stable/nn.html#torch.nn.Sequential) or a for-loop over a list of transforms.
- `SPECTROGRAM`, `F2M`, and `MEL` have been removed. Please use `Spectrogram`, `MelScale`, and `MelSpectrogram`
- Removed formatting transforms ( `LC2CL` and `BLC2CBL`): While the LC layout might be common in signal processing, support for it is out of scope of this library and transforms such as LC2CL only aid their proliferation. Please use transpose if you need this behavior.
- Removed `Scale`, `PadTrim`, `DownmixMono`: Please use division in place of `Scale` [torch.nn.functional.pad](https://pytorch.org/docs/stable/nn.html#torch.nn.functional.pad)/trim in place of `PadTrim` , [torch.mean](https://pytorch.org/docs/stable/torch.html#torch.mean) on the channel dimension in place of `DownmixMono`.
- `torchaudio.legacy` has been removed. Please use `torchaudio.load` and `torchaudio.save`
- `Spectrogram` used to be of dimension (channel, time, freq) and is now (channel, freq, time). Similarly for `MelScale`, `MelSpectrogram`, and `MFCC`, time is the last dimension. Please see our README for an explanation of the rationale behind these changes. Please use transpose to get the previous behavior.
- `MuLawExpanding` was renamed to `MuLawDecoding` as the inverse of `MuLawEncoding` ( https://github.com/pytorch/audio/pull/159)
- `SpectrogramToDB` was renamed to `AmplitudeToDB` ( https://github.com/pytorch/audio/pull/170). The input does not necessarily have to be a spectrogram and as such can be used in many more cases as the name should reflect.
New Features
- [torchaudio.compliance.kaldi.spectrogram](https://pytorch.org/audio/compliance.kaldi.html#torchaudio.compliance.kaldi.spectrogram) (https://github.com/pytorch/audio/pull/119)
- [torchaudio.compliance.kaldi.fbank](https://pytorch.org/audio/compliance.kaldi.html#torchaudio.compliance.kaldi.fbank) (https://github.com/pytorch/audio/pull/127 )
- [torchaudio.compliance.kaldi.resample_waveform](https://pytorch.org/audio/compliance.kaldi.html#torchaudio.compliance.kaldi.resample_waveform) (https://github.com/pytorch/audio/pull/134)
- [torchaudio.transforms.Resample](https://pytorch.org/audio/transforms.html#resample)(https://github.com/pytorch/audio/pull/134)
- [torchaudio.functional.istft](https://pytorch.org/audio/functional.html#torchaudio.functional.istft) ( https://github.com/pytorch/audio/pull/135 )
- [torchaudio.functional.complex_norm](https://pytorch.org/audio/functional.html#torchaudio.functional.complex_norm) (https://github.com/pytorch/audio/pull/131)
- [torchaudio.functional.angle](https://pytorch.org/audio/functional.html#torchaudio.functional.angle) (https://github.com/pytorch/audio/pull/131)
- [torchaudio.functional.magphase](https://pytorch.org/audio/functional.html#torchaudio.functional.magphase) (https://github.com/pytorch/audio/pull/131)
- [torchaudio.functional.phase_vocoder](https://pytorch.org/audio/functional.html#torchaudio.functional.phase_vocoder) (https://github.com/pytorch/audio/pull/131)
Performance
JIT and CUDA
- JIT support added to `Spectrogram`, `AmplitudeToDB`, `MelScale`, `MelSpectrogram`, `MFCC`, `MuLawEncoding`, and `MuLawDecoding`. (https://github.com/pytorch/audio/pull/118)
- CUDA support added to `Spectrogram`, `AmplitudeToDB`, `MelScale`, `MelSpectrogram`, `MFCC`, `MuLawEncoding`, and `MuLawDecoding` (https://github.com/pytorch/audio/pull/118)
Bug Fixes
- Fix `test_transforms.py` where double tensors were compared with floats (https://github.com/pytorch/audio/pull/132)
- Fix `vctk.read_audio` (issue https://github.com/pytorch/audio/issues/143) as there were issues with downsampling using `SoxEffectsChain` (https://github.com/pytorch/audio/pull/145)
- Fix segfault passing null to `sox_close` (https://github.com/pytorch/audio/pull/174)