Skip to content

GitLab

Switch branch/tag
  1. 10 Aug, 2023 1 commit
  3. 07 Aug, 2023 1 commit
    • moto's avatar
      Add merge_tokens / TokenSpan (#3535) · 30668afb
      moto authored 
      Summary:
This commit adds `merge_tokens` function which removes repeated tokens from CTC token sequences returned from `forced_align`.

Resolving repeated tokens is a necessary step and almost universal, thus it makes sense to have such helper function in torchaudio.

Pull Request resolved: https://github.com/pytorch/audio/pull/3535

Reviewed By: huangruizhe

Differential Revision: D48111202

Pulled By: mthrok

fbshipit-source-id: 25354bfa210aa5c03f8c1d3e201f253ca3761b24
      30668afb
  5. 05 Jun, 2023 1 commit
  7. 22 May, 2023 1 commit
  9. 24 Jan, 2023 1 commit
  11. 14 Nov, 2022 1 commit
  13. 10 Nov, 2022 1 commit
  15. 20 Sep, 2022 1 commit
  17. 15 Sep, 2022 1 commit
  19. 03 Aug, 2022 1 commit
    • bshall's avatar
      An implemenation of the ITU-R BS.1770-4 loudness recommendation (#2472) · 946b180a
      bshall authored 
      Summary:
I took a stab at implementing the ITU-R BS.1770-4 loudness recommendation (closes https://github.com/pytorch/audio/issues/1205). To give some more details:
- I've implemented K-weighting following csteinmetz1 instead of BrechtDeMan since it fit well with torchaudio's already implemented filters (`treble_biquad` and `highpass_biquad`).
- I've added four audio files to test compliance with the recommendation. These are linked in [this pdf](https://www.itu.int/dms_pub/itu-r/opb/rep/R-REP-BS.2217-2-2016-PDF-E.pdf). There are many more test files there but I didn't want to bog down the assets directory with too many files. Let me know if I should add or remove anything.
- I've kept many of the constant internal to the function (e.g. the block duration, overlap, and the absolute threshold gamma). I'm not sure if these should be exposed in the signature.
- I've implemented support for up to 5 channels (following both csteinmetz1 and BrechtDeMan). The recommendation includes weights for up to 24 channels. Is there any convention for how many channels to support?

I hope this is helpful! looking forward to hearing from you.

Pull Request resolved: https://github.com/pytorch/audio/pull/2472

Reviewed By: hwangjeff

Differential Revision: D38389155

Pulled By: carolineechen

fbshipit-source-id: fcc86d864c04ab2bedaa9acd941ebc4478ca6904
      946b180a
  21. 26 Feb, 2022 1 commit
    • Zhaoheng Ni's avatar
      Add apply_beamforming to torchaudio.functional (#2232) · 9c56ffb4
      Zhaoheng Ni authored 
      Summary:
This PR adds ``apply_beamforming`` method to ``torchaudio.functional``.
The method employs the beamforming weight to the multi-channel noisy spectrum to obtain the single-channel enhanced spectrum.
The input arguments are the complex-valued beamforming weight Tensor and the multi-channel noisy spectrum.

Pull Request resolved: https://github.com/pytorch/audio/pull/2232

Reviewed By: mthrok

Differential Revision: D34474561

Pulled By: nateanl

fbshipit-source-id: 2910251a8f111e65375dfb50495b6a415113f06d
      9c56ffb4
  23. 25 Feb, 2022 5 commits
  25. 10 Nov, 2021 1 commit
  27. 04 Nov, 2021 1 commit
  29. 28 Oct, 2021 1 commit
  31. 27 Oct, 2021 1 commit
  33. 26 Oct, 2021 1 commit
  35. 01 Sep, 2021 1 commit
  37. 20 Aug, 2021 2 commits
  39. 19 Aug, 2021 1 commit
  41. 14 Aug, 2021 1 commit
  43. 02 Aug, 2021 1 commit
  45. 29 Jul, 2021 1 commit
  47. 16 Jul, 2021 1 commit
  49. 03 Jun, 2021 1 commit
    • moto's avatar
      Update docs (#1550) · 0166a851
      moto authored 
      * Use `bibtex` for paper citations.
  * add `override.css` for fixing back reference.
  * wav2vec2
  * wav2letter
  * convtasnet
  * deepspeech
  * rnnt-loss
  * griffinlim
* Fix broken references in `filtering`.
* Fix note in soundfile backends.
* Tweak wav2vec2 example.
* Removes unused `pytorch_theme.css`
      0166a851
  51. 02 Jun, 2021 1 commit
  53. 22 Mar, 2021 1 commit
  55. 01 Mar, 2021 1 commit
  57. 26 Feb, 2021 1 commit
  59. 12 Feb, 2021 1 commit
  61. 04 Dec, 2020 1 commit
  63. 06 Nov, 2020 1 commit
  65. 30 Jul, 2020 1 commit
  67. 03 Jun, 2020 1 commit
    • jimchen90's avatar
      Add Bass with Biquad (#661) · a466b3c2
      jimchen90 authored 
      

* Add bass with biquad

* Update functional.py

Add the normalization coefficients

* Update test_sox_compatibility.py

In test_sox_compatibility.py file, I add two bass tests: one test sets gain = 30, atol = 1e-4, the other sets gain = 40, atol = 1.5e-4. The details can be seen in pytorch#676

* Update torchscript_consistency_impl.py

Add torchscript test

* Add flake8 test
Co-authored-by: default avatarJi Chen <jimchen90@devfair0160.h2.fair>
      a466b3c2
  69. 02 Jun, 2020 1 commit