You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Titung/urban-surveillance-mode-classifier-finetuned

YAMNet fine-tuned end-to-end (not just a frozen-embedding head) on Titung/urban-surveillance-audio-raw, for a personal safety wearable. Classes: ['Background', 'Car Crash', 'Glass Breaking', 'Gunshots', 'Screams', 'Siren', 'Tire Skidding', 'Vehicle Mechanical Sound']

This is the fine-tuned counterpart to the frozen-head baseline. Compare metrics.json against that run before deciding which to ship -- fine-tuning only wins if it improves the thin classes without collapsing generalization (check the train/val macro-F1 gap in Cell 11).

Files

saved_model/ -- full TensorFlow SavedModel (YAMNet + classifier head), input: (batch, 32000) float32 waveform at 16kHz
class_names.json -- index-to-class-name mapping (model output order)
thresholds.json -- per-class calibrated decision thresholds (recalibrated for this model)
alert_policy.json -- per-mode (driving / trek / night_walk / standby) class thresholds
metrics.json -- test macro-F1, per-class test F1, and the LRs/epochs used

Test performance

Macro-F1: 0.7222

Downloads last month: -; Downloads are not tracked for this model. How to track