Skip to content

GitLab

Switch branch/tag
  1. 23 Jan, 2023 1 commit
  3. 22 Jan, 2023 1 commit
    • moto's avatar
      Make StreamReader return PTS (#2975) · 0dd59e0d
      moto authored 
      Summary:
This commit makes `StreamReader` report PTS (presentation time stamp) of the returned chunk as well.

Example

```python
from torchaudio.io import StreamReader

s = StreamReader(...)
s.add_video_stream(...)
for (video_chunk, ) in s.stream():
    # video_chunk is Torch tensor type but has extra attribute of PTS
    print(video_chunk.pts)  # reports the PTS of the first frame of the video chunk.
```

For the backward compatibility, we introduce a `_ChunkTensor`, that is a composition
of Tensor and metadata, but works like a normal tensor in PyTorch operations.

The implementation of `_ChunkTensor` is based on [TrivialTensorViaComposition](https://github.com/albanD/subclass_zoo/blob/0eeb1d68fb59879029c610bc407f2997ae43ba0a/trivial_tensors.py#L83).

It was also suggested to attach metadata directly to Tensor object,
but the possibility to have the collision on torchaudio's metadata and new attributes introduced in
PyTorch cannot be ignored, so we use Tensor subclass implementation.

If any unexpected issue arise from metadata attribute name collision, client code can
fetch the bare Tensor and continue.

Pull Request resolved: https://github.com/pytorch/audio/pull/2975

Reviewed By: hwangjeff

Differential Revision: D42526945

Pulled By: mthrok

fbshipit-source-id: b4e9422e914ff328421b975120460f3001268f35
      0dd59e0d
  5. 15 Jan, 2023 1 commit
    • Zhaoheng Ni's avatar
      Add pre-trained pipelines for XLS-R models (#2978) · 9b7b64e4
      Zhaoheng Ni authored 
      Summary:
The PR adds three `Wav2Vec2Bundle ` pipeline objects for XLS-R models:
- WAV2VEC2_XLSR_300M
- WAV2VEC2_XLSR_1B
- WAV2VEC2_XLSR_2B

All three models use layer normalization in the feature extraction layers, hence `_normalize_waveform` is set to `True`.

Pull Request resolved: https://github.com/pytorch/audio/pull/2978

Reviewed By: hwangjeff

Differential Revision: D42501491

Pulled By: nateanl

fbshipit-source-id: 2429ec880cc14798034843381e458e1b4664dac3
      9b7b64e4
  7. 13 Jan, 2023 1 commit
  9. 06 Jan, 2023 1 commit
  11. 05 Jan, 2023 2 commits
  13. 04 Jan, 2023 1 commit
  15. 30 Dec, 2022 1 commit
  17. 22 Dec, 2022 1 commit
  19. 17 Dec, 2022 1 commit
  21. 10 Dec, 2022 1 commit
  23. 08 Dec, 2022 2 commits
  25. 07 Dec, 2022 2 commits
  27. 06 Dec, 2022 1 commit
  29. 02 Dec, 2022 1 commit
  31. 30 Nov, 2022 1 commit
  33. 29 Nov, 2022 3 commits
  35. 28 Nov, 2022 2 commits
  37. 18 Nov, 2022 1 commit
  39. 17 Nov, 2022 2 commits
  41. 15 Nov, 2022 2 commits
  43. 14 Nov, 2022 1 commit
  45. 10 Nov, 2022 2 commits
  47. 09 Nov, 2022 1 commit
  49. 08 Nov, 2022 1 commit
  51. 03 Nov, 2022 1 commit
  53. 02 Nov, 2022 2 commits
  55. 28 Oct, 2022 1 commit
  57. 20 Oct, 2022 1 commit
  59. 13 Oct, 2022 1 commit
    • moto's avatar
      Fix CTCDecoder doc (#2766) · 3e4b961d
      moto authored 
      Summary:
* Document `__call__` instead of `__init__`
* List CTCHypothesis first as it is used in combination with CTCDecoder
* Fix indentation of score method docstring

Pull Request resolved: https://github.com/pytorch/audio/pull/2766

Reviewed By: carolineechen

Differential Revision: D40349388

Pulled By: mthrok

fbshipit-source-id: 5e512e6c2b29d3533eb62d09b289154ccd1abf4c
      3e4b961d