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

Normalize and chunk audio inputs in wav2vec2 example #400

Merged
merged 2 commits into from
Nov 7, 2024
Merged

Normalize and chunk audio inputs in wav2vec2 example #400

merged 2 commits into from
Nov 7, 2024

Commits on Nov 7, 2024

  1. Correct comment in LayerNormalization implementation

    @robertknight
    robertknight committed Nov 7, 2024
    Configuration menu
    Copy the full SHA
    fbde496 View commit details
    Browse the repository at this point in the history

  2. Normalize and chunk audio inputs in wav2vec2 example 

    Improve the wav2vec2 example by:

 - Normalizing audio samples to unit mean and variance, as described in the
   wav2vec2 paper and linked issues. In the original fairseq source the
   PyTorch `layer_norm` function is used, which does the same thing.

 - Chunking the audio to improve performance when transcribing long audio
   inputs.

 - Improving the readability of the output by lower-casing the raw char
   predictions and replacing "|" with spaces.
    @robertknight
    robertknight committed Nov 7, 2024
    Configuration menu
    Copy the full SHA
    a3fd613 View commit details
    Browse the repository at this point in the history