Train a sound detector without writing code.
In GrizCam Desktop Pro, Tools → Classifiers turns the calls you have annotated into a reusable detector for that sound: a howl, a chorus, a gunshot, a bird call. Running a detector you already have is free; training a new one is part of Pro.
From your annotations to a detector.
Pick the one sound to find and the look-alikes it keeps confusing with it. GrizEars draws background examples from the parts of your finished files that hold no target, three for every positive by default, so the detector learns what your site sounds like without it.
Two optional steps make it sharper. One round of hard-negative mining scores your files, takes the background it wrongly fired on, and refits once. Augmentation trains on shifted and reverberated copies of each call, so the detector holds up in other recording conditions.
Six foundation models to listen with.
The detector builds on a bioacoustic foundation model that turns audio into numbers a classifier can read. Choose from six, including Perch 2.0 and the AVES2 family; each is a third-party open model used under its own license.
A linear probe is the default decision head. A prototype head can separate look-alike calls better when you have few negative examples.
Measured on files it never heard.
Hold back whole files, 20% by default, that the detector never trains on. When training ends, it runs on them and you review every detection: real, leave alone, or false alarm. Confirmed false alarms fold back in on a refit.
The results show precision and recall at each confidence cut-off. Set the threshold from how rare the sound really is and how many false hits per hour you can live with, and GrizEars picks the most sensitive setting that stays inside that budget.
A wolf-howl detector, built this way.
The Cry Wolf classifier was trained in GrizCam Desktop on The Cry Wolf Project's Greater Yellowstone recordings. The same classifier can run on a GrizCam in the field, flagging the call as it happens.
Before you train, the free tools find and sort the calls: free passive acoustic monitoring software.
What it asks of you.
Training needs GrizCam Desktop Pro. The first time you use a model, the app downloads its weights over the internet. On Windows, training is faster on an NVIDIA graphics card with the CUDA build.
A detector is only as good as the annotations behind it, and the hold-out review is how you find out. GrizCam Desktop is in beta, so expect change.