DistilHubert - Finetuned Cry Detector: Open-source Cry Detection Model with High Accuracy to Ensure a Peaceful Environment

Distilhubert Finetuned Cry Detector

Developed by Marcos12886

A cry detection model fine-tuned based on the distilhubert architecture, achieving outstanding performance on the evaluation set with an accuracy of 98.83%

Audio Classification

Transformers

Open Source License:Apache-2.0 #Baby cry detection #High-precision audio classification #Medical monitoring

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

🚀 distilhubert-finetuned-cry-detector

This is a fine - tuned model based on ntu - spml/distilhubert, used for cry detection with excellent evaluation results.

🚀 Quick Start

This model is a fine - tuned version of [ntu - spml/distilhubert](https://huggingface.co/ntu - spml/distilhubert) on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2255
Accuracy: 0.9883
F1: 0.9883
Precision: 0.9883
Recall: 0.9883
Confusion Matrix: [[960, 10], [6, 389]]

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

🔧 Technical Details

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e - 05
train_batch_size: 64
eval_batch_size: 64
seed: 123
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20
label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Confusion Matrix
0.3124	2.3256	100	0.2739	0.9641	0.9640	0.9640	0.9641	[[948, 22], [27, 368]]
0.2337	4.6512	200	0.2385	0.9736	0.9737	0.9737	0.9736	[[950, 20], [16, 379]]
0.2064	6.9767	300	0.2295	0.9832	0.9832	0.9832	0.9832	[[958, 12], [11, 384]]
0.2023	9.3023	400	0.2277	0.9868	0.9869	0.9870	0.9868	[[957, 13], [5, 390]]
0.2003	11.6279	500	0.2254	0.9875	0.9876	0.9876	0.9875	[[960, 10], [7, 388]]
0.2002	13.9535	600	0.2259	0.9875	0.9876	0.9876	0.9875	[[959, 11], [6, 389]]
0.1994	16.2791	700	0.2255	0.9883	0.9883	0.9883	0.9883	[[960, 10], [6, 389]]
0.1997	18.6047	800	0.2254	0.9883	0.9883	0.9883	0.9883	[[960, 10], [6, 389]]

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Tokenizers 0.19.1

📄 License

The project uses the apache - 2.0 license.

Property	Details
Library Name	transformers
Model Type	distilhubert - finetuned - cry - detector
License	apache - 2.0
Base Model	ntu - spml/distilhubert
Tags	generated_from_trainer
Metrics	accuracy, f1, precision, recall

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご