Distil-wav2vec2 Open-source Audio Classification Model - Free Identification of Adult and Children's Voices

Home

Distil Wav2vec2 Xls R Adult Child Cls 64m

Developed by bookbot

A distilled audio classification model based on XLS-R architecture for distinguishing between adult and child voices

Audio Classification

Transformers

EnglishOpen Source License:Apache-2.0 #Voice Age Classification #High-precision Audio Recognition #Lightweight XLS-R

Downloads 15

Release Time : 3/2/2022

Model Overview

This model is a distilled version based on the XLS-R architecture, specifically designed for audio classification tasks to accurately differentiate between adult and child voices.

Model Features

Efficient Distillation

A distilled version based on XLS-R architecture with reduced parameters while maintaining high performance

High Accuracy

Achieves 93.86% accuracy in adult/child voice classification tasks

Lightweight

Only 64M parameters, suitable for deployment in resource-limited environments

Model Capabilities

Audio Classification

Adult/Child Voice Recognition

Use Cases

Educational Technology

Children's Educational Applications

Identify children's voices to provide age-appropriate educational content

Enhance the age-appropriateness of educational applications

Speech Analysis

Voice Data Classification

Automatically classify voice data into adult and child categories

93.86% classification accuracy

🚀 DistilWav2Vec2 XLS-R Adult/Child Speech Classifier 64M

DistilWav2Vec2 XLS-R Adult/Child Speech Classifier is an audio classification model based on the XLS-R architecture, which is a distilled version of another model on a private adult/child speech classification dataset.

🚀 Quick Start

DistilWav2Vec2 XLS-R Adult/Child Speech Classifier is an audio classification model based on the XLS-R architecture. This model is a distilled version of wav2vec2-xls-r-adult-child-cls on a private adult/child speech classification dataset.

This model was trained using HuggingFace's PyTorch framework. All training was done on a Tesla P100, provided by Kaggle. Training metrics were logged via Tensorboard.

✨ Features

Based on the XLS - R architecture for audio classification.
A distilled version of an existing model on a private dataset.

📚 Documentation

Model

Property	Details
Model Type	`distil-wav2vec2-xls-r-adult-child-cls-64m`
#params	64M
Arch.	XLS - R
Training Data	Adult/Child Speech Classification Dataset

Evaluation Results

The model achieves the following results on evaluation:

Dataset	Loss	Accuracy	F1
Adult/Child Speech Classification	0.2571	93.86%	0.9425

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5509	1.0	191	0.3685	0.9086	0.9131
0.4543	2.0	382	0.3113	0.9247	0.9285
0.409	3.0	573	0.2723	0.9372	0.9418
0.3024	4.0	764	0.2786	0.9381	0.9417
0.3103	5.0	955	0.2571	0.9386	0.9425

Disclaimer

⚠️ Important Note

Do consider the biases which came from pre - training datasets that may be carried over into the results of this model.

Authors

DistilWav2Vec2 XLS - R Adult/Child Speech Classifier was trained and evaluated by Ananto Joyoadikusumo. All computation and development are done on Kaggle.

Framework versions

Transformers 4.17.0.dev0
Pytorch 1.10.2+cu102
Datasets 1.18.3
Tokenizers 0.11.0

📄 License

This project is licensed under the Apache 2.0 license.

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