- 03 Aug, 2021 5 commits
-
-
Caroline Chen authored
-
moto authored
-
yangarbiter authored
-
nateanl authored
-
Arijit Roy authored
-
- 02 Aug, 2021 3 commits
-
-
yangarbiter authored
-
yangarbiter authored
-
Joel Frank authored
- Renamed torchaudio.functional.create_fb_matrix to torchaudio.functional.melscale_fbanks. - Added interface with a warning for create_fb_matrix
-
- 31 Jul, 2021 2 commits
-
-
Nikita Shulga authored
-
Nikita Shulga authored
* Pin MKL to 2021.2.0 Fixes https://github.com/pytorch/pytorch/issues/62424 * Apply the same constraint for conda builds Use less-than-equals constraint to avoid dependency conflicts for python-3.6 environment
-
- 29 Jul, 2021 3 commits
-
-
yangarbiter authored
-
yangarbiter authored
-
Joel Frank authored
Summary: - Add linear_fbank method - Add LFCC in transforms
-
- 28 Jul, 2021 5 commits
-
-
yangarbiter authored
-
yangarbiter authored
-
yangarbiter authored
-
nateanl authored
-
Arijit Roy authored
-
- 27 Jul, 2021 2 commits
-
-
Zack Kneupper authored
-
moto authored
-
- 26 Jul, 2021 3 commits
-
-
yangarbiter authored
-
yangarbiter authored
-
moto authored
-
- 22 Jul, 2021 2 commits
-
-
hwangjeff authored
Rebases #1571; addresses #1569: "In 0.9.0 we are deprecating the lazy behavior of MelScale because it can make an invalid TorchScript object and it does not align with the design of torchaudio. Now in master branch, we can remove the implementation." Co-authored-by:
Pankaj Patil <pankaj.patil2099@hotmail.com> Co-authored-by:
moto <855818+mthrok@users.noreply.github.com> Co-authored-by:
hwangjeff <jeffhwang@fb.com>
-
evanjscallan authored
-
- 21 Jul, 2021 1 commit
-
-
Chin-Yun Yu authored
-
- 20 Jul, 2021 3 commits
-
-
hwangjeff authored
-
yangarbiter authored
-
yangarbiter authored
Porting Tacotron2 from https://github.com/NVIDIA/DeepLearningExamples/blob/master/PyTorch/SpeechSynthesis/Tacotron2/tacotron2/model.py
-
- 16 Jul, 2021 2 commits
-
-
hwangjeff authored
`torchaudio._internal.fft` was originally added to account for the introduction of module `torch.fft`, when `torch.fft` could refer to either a module or function. Now that `torch.fft` refers unambiguously to a module, we remove `torchaudio._internal.fft` and replace references to it with `torch.fft`.
-
nateanl authored
-
- 15 Jul, 2021 1 commit
-
-
Caroline Chen authored
-
- 14 Jul, 2021 1 commit
-
-
Joel Frank authored
-
- 12 Jul, 2021 2 commits
-
-
yangarbiter authored
The test was broken from the beginning and for a reason unrelated to ROCm, but was disabled for ROCm in https://github.com/pytorch/audio/pull/1411. https://github.com/pytorch/audio/pull/1604 fixed the test so that we are re-enabling it.
-
yangarbiter authored
* [BC-Breaking] Default to PCM_16 for flac on soundfile backend Resolving https://github.com/pytorch/audio/issues/1592 The test backend/soundfile/save_test.py::TestFileObject::test_fileobj_flac is failing due to the fact that when soundfile.write received subtype=None (for flac files), it would fall back to 'PCM_16'. But in the same time, torchaudio will use 'PCM_24', which would result in distorted signal. This commit fixed this issue by changing the default bit-per-sample of for flac files from 24-bit to 16-bit.
-
- 08 Jul, 2021 1 commit
-
-
Caroline Chen authored
-
- 07 Jul, 2021 2 commits
-
-
Caroline Chen authored
-
Caroline Chen authored
-
- 28 Jun, 2021 2 commits
-
-
Eli Uriegas authored
No longer needed for Python 3.9 Signed-off-by:Eli Uriegas <eliuriegas@fb.com>
-
Caroline Chen authored
-