Trillsson3-ft-keyword-spotting-11 Open-source Audio Classification Model

Trillsson3 Ft Keyword Spotting 11

Developed by vumichien

An audio classification model based on the TRillsson3 architecture, fine-tuned on the superb dataset for keyword recognition tasks

Audio Classification

Transformers

#Keyword Recognition #High Accuracy Audio Classification #Non-Semantic Speech Processing

Downloads 32

Release Time : 10/22/2022

Model Overview

This model is an audio classification model based on the TRillsson3 architecture, specifically optimized for keyword recognition tasks. After fine-tuning on the superb dataset, it achieved an accuracy of 90.88% on the evaluation set.

Model Features

High Accuracy

Achieved a high accuracy of 90.88% on the evaluation set

Based on TRillsson3 Architecture

Based on the advanced TRillsson3 non-semantic speech representation architecture

Professional Fine-Tuning

Professionally fine-tuned on the superb dataset to optimize keyword recognition performance

Model Capabilities

Audio Classification

Keyword Recognition

Speech Feature Extraction

Use Cases

Voice Interaction

Voice Assistant Wake Word Detection

Used to detect wake words for voice assistants

High accuracy in recognizing specific keywords

Voice Command Recognition

Recognize keywords in user voice commands

Security Monitoring

Abnormal Speech Detection

Detect specific keywords or abnormal speech in audio streams

🚀 trillsson3-ft-keyword-spotting-11

This model is a fine - tuned version of vumichien/nonsemantic - speech - trillsson3 on the superb dataset. It offers a practical solution for audio classification tasks, specifically keyword spotting. The model achieves remarkable results on the evaluation set, with a loss of 0.3166 and an accuracy of 0.9088.

📚 Documentation

Model description

This model is a fine - tuned version of vumichien/nonsemantic-speech-trillsson3 on the superb dataset. It achieves the following results on the evaluation set:

Loss: 0.3166
Accuracy: 0.9088

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

🔧 Technical Details

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 32
eval_batch_size: 32
seed: 0
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.9219	1.0	399	1.2023	0.6217
0.9604	2.0	798	0.5437	0.8117
0.7608	3.0	1197	0.4222	0.8888
0.7045	4.0	1596	0.3881	0.8932
0.659	5.0	1995	0.3706	0.8847
0.6541	6.0	2394	0.3553	0.8917
0.6448	7.0	2793	0.3482	0.8953
0.6288	8.0	3192	0.3409	0.8989
0.641	9.0	3591	0.3297	0.9051
0.6369	10.0	3990	0.3325	0.9042
0.6218	11.0	4389	0.3250	0.9064
0.6247	12.0	4788	0.3312	0.8959
0.6284	13.0	5187	0.3217	0.9069
0.6213	14.0	5586	0.3301	0.8978
0.6274	15.0	5985	0.3180	0.9081
0.627	16.0	6384	0.3257	0.9020
0.6227	17.0	6783	0.3193	0.9056
0.6192	18.0	7182	0.3199	0.9066
0.6075	19.0	7581	0.3183	0.9073
0.6196	20.0	7980	0.3166	0.9088

Framework versions

Transformers 4.23.0.dev0
Pytorch 1.12.1+cu113
Datasets 2.6.1
Tokenizers 0.13.1

Property	Details
Tags	audio - classification, generated_from_trainer
Datasets	superb
Metrics	accuracy
Model Name	trillsson3 - ft - keyword - spotting - 11

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