Distilhubert Finetuned Cry Detector
A cry detection model fine-tuned based on the distilhubert architecture, achieving outstanding performance on the evaluation set with an accuracy of 98.83%
Downloads 22
Release Time : 7/17/2024
Model Overview
This model is specifically designed to detect crying signals in audio, suitable for scenarios such as infant monitoring and medical surveillance
Model Features
High accuracy
Achieves 98.83% accuracy and F1 score on the evaluation set
Lightweight architecture
Based on the distilled DistilHuBERT architecture, reducing computational requirements while maintaining performance
Optimized training parameters
Utilizes cosine annealing with restarts learning rate scheduling and label smoothing techniques
Model Capabilities
Audio classification
Cry detection
Real-time audio analysis
Use Cases
Infant monitoring
Smart infant monitoring system
Real-time monitoring of baby cries and alerting caregivers
Accurate recognition rate of 98.83%
Medical monitoring
Patient emotional monitoring
Detecting crying signals from patients in distress
Featured Recommended AI Models
Š 2025AIbase