Skip to content

GitLab

"examples/vscode:/vscode.git/clone" did not exist on "ca1a22296d02ab44547a33c1bb7e5a4015a2f843"
Switch branch/tag
  1. 10 May, 2022 2 commits
    • Zhaoheng Ni's avatar
      Add diagonal_loading optional to rtf_power (#2369) · da1e83cc
      Zhaoheng Ni authored 
      Summary:
When computing the MVDR beamforming weights using the power iteration method, the PSD matrix of noise can be applied with diagonal loading to improve the robustness. This is also applicable to computing the RTF matrix (See https://github.com/espnet/espnet/blob/master/espnet2/enh/layers/beamformer.py#L614 as an example). This also aligns with current `torchaudio.transforms.MVDR` module to keep the consistency.

This PR adds the `diagonal_loading` argument with `True` as default value to `torchaudio.functional.rtf_power`.

Pull Request resolved: https://github.com/pytorch/audio/pull/2369

Reviewed By: carolineechen

Differential Revision: D36204130

Pulled By: nateanl

fbshipit-source-id: 93a58d5c2107841a16c4e32f0c16ab0d6b2d9420
      da1e83cc
    • Zhaoheng Ni's avatar
      Add SoudenMVDR module (#2367) · aed5eb88
      Zhaoheng Ni authored 
      Summary:
Add a new design of MVDR module.
The `SoudenMVDR` module supports the method proposed by [Souden et, al.](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.725.673&rep=rep1&type=pdf).
The input arguments are:
- multi-channel spectrum.
- PSD matrix of target speech.
- PSD matrix of noise.
- reference channel in the microphone array.
- diagonal_loading option to enable or disable diagonal loading in matrix inverse computation.
- diag_eps for computing the inverse of the matrix.
- eps for computing the beamforming weight.

The output of the module is the single-channel complex-valued spectrum for the enhanced speech.

Pull Request resolved: https://github.com/pytorch/audio/pull/2367

Reviewed By: hwangjeff

Differential Revision: D36198015

Pulled By: nateanl

fbshipit-source-id: 4027f4752a84aaef730ef3ea8c625e801cc35527
      aed5eb88
  3. 06 May, 2022 1 commit
    • moto's avatar
      Refactor smoke test executions (#2365) · 6a8a28bb
      moto authored 
      Summary:
The smoke test jobs simply perform `import torchaudio` to check
if the package artifacts are sane.

Originally, the CI was executing it in the root directory.
This was fine unless the source code is checked out.
When source code is checked out, performing `import torchaudio` in
root directory would import source torchaudio directory, instead of the
installed package.

This error is difficult to notice, so this commit introduces common script to
perform the smoke test, while moving out of root directory.

Pull Request resolved: https://github.com/pytorch/audio/pull/2365

Reviewed By: carolineechen

Differential Revision: D36202069

Pulled By: mthrok

fbshipit-source-id: 4396f85fec5c54869ada4c08f51304539f1b05cf
      6a8a28bb
  5. 26 Apr, 2022 1 commit
  7. 21 Apr, 2022 1 commit
    • hwangjeff's avatar
      Change underlying implementation of RNN-T hypothesis to tuple (#2339) · 6b242c29
      hwangjeff authored 
      Summary:
PyTorch Lite, which is becoming a standard for mobile PyTorch usage, does not support containers containing custom classes. Consequently, because TorchAudio's RNN-T decoder currently returns and accepts lists of `Hypothesis` namedtuples, it is not compatible with PyTorch Lite. This PR resolves said incompatibility by changing the underlying implementation of `Hypothesis` to tuple.

Pull Request resolved: https://github.com/pytorch/audio/pull/2339

Reviewed By: nateanl

Differential Revision: D35806529

Pulled By: hwangjeff

fbshipit-source-id: 9cbae5504722390511d35e7f9966af2519ccede5
      6b242c29
  9. 18 Apr, 2022 1 commit
  11. 12 Apr, 2022 1 commit
    • hwangjeff's avatar
      Add Conformer RNN-T model prototype (#2322) · b0c8e239
      hwangjeff authored 
      Summary:
Adds Conformer RNN-T model as prototype feature, by way of factory functions `conformer_rnnt_model` and `conformer_rnnt_base`, which instantiates a baseline version of the model. Also includes the following:
- Modifies `Conformer` to accept arguments `use_group_norm` and `convolution_first` to pass to each of its `ConformerLayer` instances.
- Makes `_Predictor` an abstract class and introduces `_EmformerEncoder` and `_ConformerEncoder`.
- Introduces tests for `conformer_rnnt_model`.
- Adds docs.

Pull Request resolved: https://github.com/pytorch/audio/pull/2322

Reviewed By: xiaohui-zhang

Differential Revision: D35565987

Pulled By: hwangjeff

fbshipit-source-id: cb37bb0477ae3d5fcf0b7124f334f4cbb89b5789
      b0c8e239
  13. 08 Apr, 2022 1 commit
    • moto's avatar
      Add devices/properties badges (#2321) · 72ae755a
      moto authored 
      Summary:
Add badges of supported properties and devices to functionals and transforms.

This commit adds `.. devices::` and `.. properties::` directives to sphinx.

APIs with these directives will have badges (based off of shields.io) which link to the
page with description of these features.

Continuation of https://github.com/pytorch/audio/issues/2316
Excluded dtypes for further improvement, and actually added badges to most of functional/transforms.

Pull Request resolved: https://github.com/pytorch/audio/pull/2321

Reviewed By: hwangjeff

Differential Revision: D35489063

Pulled By: mthrok

fbshipit-source-id: f68a70ebb22df29d5e9bd171273bd19007a81762
      72ae755a
  15. 01 Apr, 2022 1 commit
    • moto's avatar
      Loosen atol for melscale batch test for Windows (#2305) · d65a0f3e
      moto authored 
      Summary:
The `transforms.batch_consistency_test.TestTransforms` test is failing for Windows.

https://app.circleci.com/pipelines/github/pytorch/audio/10093/workflows/bbe003c4-3dfa-4729-a3e1-c942ab1243d4/jobs/594272

```
>       self.assertEqual(items_result, batch_result, rtol=rtol, atol=atol)
E       AssertionError: Tensor-likes are not close!
E
E       Mismatched elements: 28 / 196608 (0.0%)
E       Greatest absolute difference: 2.0023435354232788e-07 at index (1, 1, 127, 100) (up to 1e-08 allowed)
E       Greatest relative difference: 0.0005069057444598896 at index (0, 0, 114, 129) (up to 1e-05 allowed)
```

The value of atol==1e-08 seems very strict but all the other batch
consistency tests are passing.

The violation is for very small number of samples, which looks
suspicious, but I think it is okay to reduce it to `1e-06` for Windows.

`1e-06` is still more strict than the majority of the comparison tests we have.

Pull Request resolved: https://github.com/pytorch/audio/pull/2305

Reviewed By: hwangjeff

Differential Revision: D35298056

Pulled By: mthrok

fbshipit-source-id: a7d20f408c16cff7d363f4a9462c64e19d1c99f7
      d65a0f3e
  17. 31 Mar, 2022 2 commits
    • moto's avatar
      Randomize initial phase of sinusoid data in test (#2301) · c6c6b689
      moto authored 
      Summary:
This commit update `get_sinusoid` function in test utility so that
when a multi channel is requested, non-primal channel have randomized
initial phase.

This adds some variety in test data which should not break the tests.
Currently `get_sinusoid` returns identical waveforms for all the channels.
This multi channel support was added just to mock the input data so that
it is easy to test features with multi-channel inputs, so tests should not be
expecting the all channels to be identical.

When working on numerical parity, it is more useful if the raw waveforms
are somewhat different.

Image: waveforms generated by `get_sinusoid` after the change. left: 1st channel, right: 2nd channel
<img width="524" alt="Screen Shot 2022-03-31 at 10 06 17 AM" src="https://user-images.githubusercontent.com/855818/161111163-1ea58ff6-51ee-4e37-bcd6-411041dd2603.png">

Pull Request resolved: https://github.com/pytorch/audio/pull/2301

Reviewed By: hwangjeff

Differential Revision: D35291689

Pulled By: mthrok

fbshipit-source-id: 9160d07ccdd1494acb6d41cb07ac434c0676dbfd
      c6c6b689
    • moto's avatar
      Move Kaldi comp tests to corresponding module (#2303) · ec552b69
      moto authored 
      Summary:
Tests on `torchaudio.compliance.kaldi` were scattered at different places.
This commit put all of them in dedicated `test/torchaudio_unittest/compliance/kaldi/`
directory.

Pull Request resolved: https://github.com/pytorch/audio/pull/2303

Reviewed By: nateanl

Differential Revision: D35288400

Pulled By: mthrok

fbshipit-source-id: 1426f236bc7786539d7a3110f992ad6220a52f46
      ec552b69
  19. 25 Mar, 2022 1 commit
  21. 22 Mar, 2022 1 commit
    • moto's avatar
      Add download utility specialized for torchaudio (#2283) · 64b98521
      moto authored 
      Summary:
In recent updates, torchaudio added features that download assets/models from
download.pytorch.org/torchaudio.

To reduce the code duplication, the implementations uses utilities from
``torch.hub``, but still, there are patterns repeated in implementing
the fetch mechanism, notably cache and local file path handling.

This commit introduces the utility function that handles
download/cache/local path management that can be used for
fetching pre-trained model data.

Pull Request resolved: https://github.com/pytorch/audio/pull/2283

Reviewed By: carolineechen

Differential Revision: D35050469

Pulled By: mthrok

fbshipit-source-id: 219dd806f9a96c54d2d31e981c1bbe282772702b
      64b98521
  23. 04 Mar, 2022 2 commits
    • moto's avatar
      Flush and reset internal state after seek (#2264) · 7e1afc40
      moto authored 
      Summary:
This commit adds the following behavior to `seek` so that `seek`
works after a frame is decoded.

1. Flush the decoder buffer.
2. Recreate filter graphs (so that internal state is re-initialized)
3. Discard the buffered tensor. (decoded chunks)

Also it disallows negative values for seek timestamp.

Pull Request resolved: https://github.com/pytorch/audio/pull/2264

Reviewed By: carolineechen

Differential Revision: D34497826

Pulled By: mthrok

fbshipit-source-id: 8b9a5bf160dfeb15f5cced3eed2288c33e2eb35d
      7e1afc40
    • moto's avatar
      Make Streamer fail if an invalid option is provided (#2263) · 04875eef
      moto authored 
      Summary:
`torchaudio.prototype.io.Streamer` class takes context dependant options
as `option` argument in the form of mappings of strings.

Currently there is no check if the provided options were valid for
the given input.

This commit adds the check and raise an error if an invalid erro is given.

This is analogous to `ffmpeg` command error handling.

```
$ ffmpeg -foo
...
Unrecognized option 'foo'.
```

Pull Request resolved: https://github.com/pytorch/audio/pull/2263

Reviewed By: hwangjeff

Differential Revision: D34495111

Pulled By: mthrok

fbshipit-source-id: cd068de0dc1d1273bdd5d40312c3faccb47b253f
      04875eef
  25. 26 Feb, 2022 2 commits
  27. 25 Feb, 2022 5 commits
  29. 24 Feb, 2022 1 commit
  31. 17 Feb, 2022 2 commits
    • Zhaoheng Ni's avatar
      Refactor batch consistency test in functional (#2245) · 9cf59e75
      Zhaoheng Ni authored 
      Summary:
In batch_consistency tests, the `assert_batch_consistency` method only accepts single Tensor, which is not applicable to some methods. For example, `lfilter` and `filtfilt` requires three Tensors as the arguments, hence they don't follow `assert_batch_consistency` in the tests.
This PR refactors the test to accept a tuple of Tensors which have `batch` dimension. For the other arguments like `int` or `str`, they are given as `*args` after the tuple.

Pull Request resolved: https://github.com/pytorch/audio/pull/2245

Reviewed By: mthrok

Differential Revision: D34273035

Pulled By: nateanl

fbshipit-source-id: 0096b4f062fb4e983818e5374bed6efc7b15b056
      9cf59e75
    • Zhaoheng Ni's avatar
      Add unit tests for PyTorch Lightning modules of emformer_rnnt recipes (#2240) · b5d77b15
      Zhaoheng Ni authored 
      Summary:
- Refactor the current `LibriSpeechRNNTModule`'s unit test.
- Add unit tests for `TEDLIUM3RNNTModule` and `MuSTCRNNTModule`
- Replace the lambda with partial in `TEDLIUM3RNNTModule` to pass the lightning unit test.

Pull Request resolved: https://github.com/pytorch/audio/pull/2240

Reviewed By: mthrok

Differential Revision: D34285195

Pulled By: nateanl

fbshipit-source-id: 4f20749c85ddd25cbb0eafc1733c64212542338f
      b5d77b15
  33. 16 Feb, 2022 2 commits
    • Zhaoheng Ni's avatar
      Refactor torchscript consistency test in functional (#2246) · 87d79889
      Zhaoheng Ni authored 
      Summary:
In torchscript_consistency tests, the `func` in each test method only accepts one `tensor` as the argument, for the other arguments of `F.xyz` method, they need to be defined inside the `func`. If there is no `Tensor` argument in `F.xzy`, the tests use a `dummy` tensor which is not used anywhere. In this PR, we refactor ``_assert_consistency`` and ``_assert_consistency_complex`` to accept a tuple of inputs instead of just one `tensor`.

Pull Request resolved: https://github.com/pytorch/audio/pull/2246

Reviewed By: carolineechen

Differential Revision: D34273057

Pulled By: nateanl

fbshipit-source-id: a3900edb3b2c58638e513e1490279d771ebc3d0b
      87d79889
    • Zhaoheng Ni's avatar
      Add complex dtype support in functional autograd test (#2244) · eeba91dc
      Zhaoheng Ni authored 
      Summary:
In autograd tests, to guarantee the precision, the dtype of Tensors are converted to `torch.float64` if they are real. However, the complex dtype is not considered. This PR adds `self.complex_dtype` support to the inputs.

Pull Request resolved: https://github.com/pytorch/audio/pull/2244

Reviewed By: mthrok

Differential Revision: D34272998

Pulled By: nateanl

fbshipit-source-id: e8698a74d7b8d99ee0fcb5f5cb5f2ffc8c80b9b5
      eeba91dc
  35. 15 Feb, 2022 1 commit
  37. 11 Feb, 2022 2 commits
  39. 09 Feb, 2022 2 commits
    • hwangjeff's avatar
      Clean up Emformer (#2207) · 87d7694d
      hwangjeff authored 
      Summary:
- Make `segment_length` a required argument rather than optional argument to force users to consciously choose input segment lengths for their use cases.
- Clarify expected input shapes in API documentation.
- Adjust `infer` tests to reflect expected usage.
- Add assertion for input shape for `infer`.

Pull Request resolved: https://github.com/pytorch/audio/pull/2207

Reviewed By: mthrok

Differential Revision: D34101205

Pulled By: hwangjeff

fbshipit-source-id: 1d1233d5edee5818d4669b4e47d44559e7ebb304
      87d7694d
    • hwangjeff's avatar
      Fix librosa calls (#2208) · e5d567c9
      hwangjeff authored 
      Summary:
Yesterday's release of librosa 0.9.0 made args keyword-only and changed default padding from "reflect" to "zero" for some functions. This PR adjusts callsites in our tutorials and tests accordingly.

Pull Request resolved: https://github.com/pytorch/audio/pull/2208

Reviewed By: mthrok

Differential Revision: D34099793

Pulled By: hwangjeff

fbshipit-source-id: 4e2642cdda8aae6d0a928befaf1bbb3873d229bc
      e5d567c9
  41. 02 Feb, 2022 1 commit
  43. 01 Feb, 2022 2 commits
    • hwangjeff's avatar
      Move ASR features out of prototype (#2187) · aca5591c
      hwangjeff authored 
      Summary:
Moves ASR features out of `torchaudio.prototype`. Specifically, merges contents of `torchaudio.prototype.models` into `torchaudio.models` and contents of `torchaudio.prototype.pipelines` into `torchaudio.pipelines` and updates refs, tests, and docs accordingly.

Pull Request resolved: https://github.com/pytorch/audio/pull/2187

Reviewed By: nateanl, mthrok

Differential Revision: D33918092

Pulled By: hwangjeff

fbshipit-source-id: f003f289a7e5d7d43f85b7c270b58bdf2ed6344c
      aca5591c
    • Caroline Chen's avatar
      Add CTC decoder timesteps (#2184) · d43ce015
      Caroline Chen authored 
      Summary:
add timesteps field to CTC decoder hypotheses, corresponding to the time step of occurrences of non-blank tokens

Pull Request resolved: https://github.com/pytorch/audio/pull/2184

Reviewed By: mthrok

Differential Revision: D33905530

Pulled By: carolineechen

fbshipit-source-id: c575d25655fcf252754ee3c2447949a4c059461a
      d43ce015
  45. 27 Jan, 2022 2 commits
    • Caroline Chen's avatar
      Add no lm support for CTC decoder (#2174) · 4c3fa875
      Caroline Chen authored 
      Summary:
Add support for CTC lexicon decoder without LM support by adding a non language model `ZeroLM` that returns score 0 for everything. Generalize the decoder class/API a bit to support this, adding it as an option for the kenlm decoder at the moment (will likely be separated out from kenlm when adding support for other kinds of LMs in the future)

Pull Request resolved: https://github.com/pytorch/audio/pull/2174

Reviewed By: hwangjeff, nateanl

Differential Revision: D33798674

Pulled By: carolineechen

fbshipit-source-id: ef8265f1d046011b143597b3b7c691566b08dcde
      4c3fa875
    • moto's avatar
      Add `is_ffmpeg_available` in test (#2170) · 39fe9df6
      moto authored 
      Summary:
Part of https://github.com/pytorch/audio/issues/2164.
To make the tests introduced in https://github.com/pytorch/audio/issues/2164 skippable if ffmpeg features are not available,
this commit adds `is_ffmpeg_available`.

The availability of the features depend on two factors;
1. If it was enabled at build.
2. If the ffmpeg libraries are found at runtime.

A simple way (for OSS workflow) to detect these is simply checking if
`libtorchaudio_ffmpeg` presents and can be loaded without a failure.

To facilitate this, this commit changes the
`torchaudio._extension._load_lib` to return boolean result.

Pull Request resolved: https://github.com/pytorch/audio/pull/2170

Reviewed By: carolineechen

Differential Revision: D33797695

Pulled By: mthrok

fbshipit-source-id: 85e767fc06350b8f99de255bc965b8c92b8cfe97
      39fe9df6
  47. 26 Jan, 2022 3 commits