GitLab

* Resolves https://github.com/pytorch/audio/issues/1095

- yesno
- librispeech
- libritts
- speechcommands
Co-authored-by: krishnakalyan3 <skalyan@cloudera.com>
Co-authored-by: Vincent Quenneville-Belair <vincentqb@gmail.com>

This reverts commit 09a6fca1.

* Import torchaudio #1034 70f429a4

Summary: Import torchaudio #1027 0cf4b8a9

Reviewed By: vincentqb, cpuhrsch

Differential Revision: D24958707

fbshipit-source-id: d06dd6b59197cc2c16bec5a9012cbf33a172b6b3

* Import torchaudio #1066 4406a6bb

Summary: Import up to #1066

Reviewed By: cpuhrsch

Differential Revision: D25373068

fbshipit-source-id: 890d36a25259b93428b3037c3123ff5a2cacfa04

* Add griffinlim and DB_to_amplitude
* Fix Dataset docstring
* Fix other formatting
Co-authored-by: krishnakalyan3 <skalyan@cloudera.com>

no longer allow to download the dataset directly. deprecate: download and url. add language.

Currently `libsox` on Linux is compiled with GPU OpenMP and it interferes with the version PyTorch uses (Intel in case of binary distribution). This PR disables OpenMP support for `libsox`, while we investigate the way to use the same OpenMP as PyTorch's version.

Co-authored-by: krishnakalyan3 <skalyan@cloudera.com>

Co-authored-by: Vincent QB <vincentqb@users.noreply.github.com>

* Import torchaudio #996 758f6c2a

Reviewed By: cpuhrsch

Differential Revision: D24606263

fbshipit-source-id: 4301b1df84d20c671783ec34c52d5b257374abf1

* Import torchaudio #1004 5e54c770

Summary: Import torchaudio up to #1004 5e54c770

Reviewed By: vincentqb, cpuhrsch

Differential Revision: D24841498

fbshipit-source-id: 3829130636f36779d84f01ff0d0120b80b2396d7

Co-authored-by: Vincent QB <vincentqb@users.noreply.github.com>