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 b2ai speaker verification functions #87

Merged
merged 18 commits into from
Jul 11, 2024
Merged

Add b2ai speaker verification functions #87

merged 18 commits into from
Jul 11, 2024

Commits on Jul 5, 2024

  1. Add b2ai speaker verification functions

    @ibevers
    ibevers committed Jul 5, 2024
    Configuration menu
    Copy the full SHA
    333d6a1 View commit details
    Browse the repository at this point in the history

Commits on Jul 6, 2024

  1. Add conditional to prevent large model run on GitHub

    @ibevers
    ibevers committed Jul 6, 2024
    Configuration menu
    Copy the full SHA
    b170c3e View commit details
    Browse the repository at this point in the history

  2. Get tests running correctly

    @ibevers
    ibevers committed Jul 6, 2024
    Configuration menu
    Copy the full SHA
    ee9640f View commit details
    Browse the repository at this point in the history

  3. Add asserts to tests

    @ibevers
    ibevers committed Jul 6, 2024
    Configuration menu
    Copy the full SHA
    b9357e3 View commit details
    Browse the repository at this point in the history

  4. Reformat

    @ibevers
    ibevers committed Jul 6, 2024
    Configuration menu
    Copy the full SHA
    e6f39eb View commit details
    Browse the repository at this point in the history

Commits on Jul 10, 2024

  1. Add support for IIR filter-based resampling to resample_audios

    @ibevers
    ibevers committed Jul 10, 2024
    Configuration menu
    Copy the full SHA
    0a450ce View commit details
    Browse the repository at this point in the history

Commits on Jul 11, 2024

  1. Update to use new resample method, SpeechBrainModel, and DeviceType

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    7967c39 View commit details
    Browse the repository at this point in the history

  2. Remove resampling code--assuming that the low pass in the IIR resampl… 

    …ing is not necessary since low pass filtering is done by default in torchaudio
    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    4aec278 View commit details
    Browse the repository at this point in the history

  3. Add checks for model training sample rate.

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    ccbbdcf View commit details
    Browse the repository at this point in the history

  4. Update to use SpeechBrainEmbeddings, cosine_similarity, and a threshold

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    b55e22d View commit details
    Browse the repository at this point in the history

  5. Use mono audio fixture in test

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    5940a26 View commit details
    Browse the repository at this point in the history

  6. Make input a list of tuples of audios

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    a45d12e View commit details
    Browse the repository at this point in the history

  7. Update threshold to .25 to match speechbrain.inference.speaker

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    6283e55 View commit details
    Browse the repository at this point in the history

  8. Change default device to None

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    20859c8 View commit details
    Browse the repository at this point in the history

  9. Make training sample rate a constant

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    97ce40e View commit details
    Browse the repository at this point in the history

  10. Remove torchaudio from resampling

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    eafefd9 View commit details
    Browse the repository at this point in the history

  11. Call _select_device_and_dtype in every case

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    62c95b4 View commit details
    Browse the repository at this point in the history

  12. Update resampling to handle stereo audio

    @ibevers
    ibevers committed Jul 11, 2024
    Configuration menu
    Copy the full SHA
    d890ea7 View commit details
    Browse the repository at this point in the history