UCSD-E4E / PyHa

A repo designed to convert audio-based "weak" labels to "strong" intraclip labels. Provides a pipeline to compare automated moment-to-moment labels to human labels. Methods range from DSP based foreground-background separation, cross-correlation based template matching, as well as bird presence sound event detection deep learning models!
Other
16 stars 11 forks source link

Birdnet dsp segmentation reverse engineering #175

Closed JacobGlennAyers closed 7 months ago

JacobGlennAyers commented 11 months ago

Changes I know of as of right now -

  1. Have to update the readme for the new model
  2. Have to change the pyha tutorial back I am sure others might be noticed as it is reviewed.