1. 15 Oct, 2021 1 commit
  2. 11 Oct, 2021 1 commit
    • moto's avatar
      Store n_bits in WaveRNN (#1847) · 498722b5
      moto authored
      Move the computation of `#classes -> #bits` to the constructor of WaveRNN and attach it to the instance, so that it can be reused elsewhere.
      498722b5
  3. 23 Aug, 2021 1 commit
  4. 27 May, 2021 1 commit
    • moto's avatar
      Add wav2vec2.0 model (#1529) · e6886a4d
      moto authored
      - TorchScript-able `Wav2Vec2Model` class
      - Factory functions for three configurations presented in the paper 
        - `wav2vec2_base`
        - `wav2vec2_large`
        - `wav2vec2_large_lv60k`
      e6886a4d
  5. 11 May, 2021 1 commit
  6. 01 Oct, 2020 1 commit
  7. 28 Sep, 2020 1 commit
  8. 05 Aug, 2020 1 commit
    • moto's avatar
      [CI] Run unit test with non-editable installation (#845) · 9ba02d5b
      moto authored
      We have been running unit test with editable installation. (i.e. `python setup.py develop`), with which we missed issues like #842. 
      
      This CC makes installation in CI non-editable, and change test directory structure so that the source code will not shadow the installed version of `torchaudio`. With simple `pytest test`, `pytest` modifies `sys.path` and prepend checked out repository, which shadows the installed version.
      
      To remedy this, the whole test suites has been moved from `./test` to `./test/torchaudio_unittest`. This adds nice module structure to our test code and we can do absolute import in each test module, which makes it possible again to run test with `python -m unittest torchaudio_unittest/XXX.py`
      
      This change does not affect the regular development process (`python setup.py develop` && `pytest test`)
      9ba02d5b
  9. 29 Jul, 2020 1 commit
  10. 17 Jul, 2020 1 commit
  11. 08 Jul, 2020 1 commit
    • jimchen90's avatar
      Add WaveRNN Model (#735) · 68cc72da
      jimchen90 authored
      
      
      * upsamplenetwork
      
      * update variable names
      
      * update variable name
      
      * add wavernn model
      
      * update test
      
      * update format
      
      * update format
      
      * update format
      
      * fix conflicts and add transpose
      
      * import update
      
      * update transpose
      
      * update format
      
      * update docstring
      
      * add n_channel in input
      
      * add comment
      
      * update docstring
      
      * update docstring
      Co-authored-by: default avatarJi Chen <jimchen90@devfair0160.h2.fair>
      68cc72da
  12. 01 Jul, 2020 1 commit
  13. 29 Jun, 2020 1 commit
  14. 23 Jun, 2020 1 commit
  15. 16 Jun, 2020 2 commits
  16. 28 Apr, 2020 1 commit
    • Tomás Osório's avatar
      Add model Wav2Letter (#462) · d678357f
      Tomás Osório authored
      * add wav2letter model
      
      * add unit_test to model
      
      * add docstrings
      
      * add documentation
      
      * fix minor error, change logic on forward
      
      * update padding same with ceil
      
      * add inline typing and minor fixes to docstrings
      
      * remove python2
      
      * add formula do docstrings, change param name
      
      * add test with mfcc, add pytest
      
      * fix bug, update docstrings
      
      * change parameter name
      d678357f