Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add Audio Spectogram Transformer #19981

Merged
merged 37 commits into from
Nov 21, 2022
Merged

Add Audio Spectogram Transformer #19981

merged 37 commits into from
Nov 21, 2022

Commits on Nov 21, 2022

  1. First draft

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    8c10464 View commit details
    Browse the repository at this point in the history

  2. Make conversion script work

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    353ead3 View commit details
    Browse the repository at this point in the history

  3. Add id2label mapping, run code quality

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    f996abe View commit details
    Browse the repository at this point in the history

  4. Fix copies

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    7006ed8 View commit details
    Browse the repository at this point in the history

  5. Add first draft of feature extractor

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    488e7e5 View commit details
    Browse the repository at this point in the history

  6. Update conversion script to use feature extractor

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    6a27c2e View commit details
    Browse the repository at this point in the history

  7. Make more tests pass

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    e8feefc View commit details
    Browse the repository at this point in the history

  8. Add docs

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    c0ec268 View commit details
    Browse the repository at this point in the history

  9. update input_features to input_values + pad by default to max length

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    d952e5f View commit details
    Browse the repository at this point in the history

  10. Fix doc tests

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    3547d7c View commit details
    Browse the repository at this point in the history

  11. Add feature extractor tests

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    0047122 View commit details
    Browse the repository at this point in the history

  12. Add proper padding/truncation to feature extractor

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    56aafc5 View commit details
    Browse the repository at this point in the history

  13. Add support for conversion of all audioset checkpoints

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    f194e9d View commit details
    Browse the repository at this point in the history

  14. Improve docs and extend conversion script

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    df8575c View commit details
    Browse the repository at this point in the history

  15. Fix README

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    a08338f View commit details
    Browse the repository at this point in the history

  16. Rename spectogram to spectrogram

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    1628536 View commit details
    Browse the repository at this point in the history

  17. Fix copies

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    9dede0c View commit details
    Browse the repository at this point in the history

  18. Add integration test

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    fdead74 View commit details
    Browse the repository at this point in the history

  19. Remove dummy conv

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    70c948a View commit details
    Browse the repository at this point in the history

  20. Update to ast

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    fd10b76 View commit details
    Browse the repository at this point in the history

  21. Update organization

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    341ade2 View commit details
    Browse the repository at this point in the history

  22. Fix init

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    5685d73 View commit details
    Browse the repository at this point in the history

  23. Rename model to AST

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    a0e7d50 View commit details
    Browse the repository at this point in the history

  24. Add require_torchaudio annotator

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    19cf9f6 View commit details
    Browse the repository at this point in the history

  25. Move import of ASTFeatureExtractor under a is_speech_available

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    6588eba View commit details
    Browse the repository at this point in the history

  26. Fix rebase

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    3de1686 View commit details
    Browse the repository at this point in the history

  27. Add pipeline config

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    3b36797 View commit details
    Browse the repository at this point in the history

  28. Update name of classifier head

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    0a8afca View commit details
    Browse the repository at this point in the history

  29. Rename time_dimension and frequency_dimension for clarity

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    4deea23 View commit details
    Browse the repository at this point in the history

  30. Remove print statement

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    8113ed1 View commit details
    Browse the repository at this point in the history

  31. Fix pipeline test

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    3154869 View commit details
    Browse the repository at this point in the history

  32. Fix pipeline test

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    4282f68 View commit details
    Browse the repository at this point in the history

  33. Fix index table

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    7e38d96 View commit details
    Browse the repository at this point in the history

  34. Fix init

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    519481c View commit details
    Browse the repository at this point in the history

  35. Fix conversion script

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    5dbf899 View commit details
    Browse the repository at this point in the history

  36. Rename to ForAudioClassification

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    369ed79 View commit details
    Browse the repository at this point in the history

  37. Fix index table

    Niels Rogge authored and Niels Rogge committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    b8e31b9 View commit details
    Browse the repository at this point in the history