Is_Vinyl_Scratched_Or_Not Open-Source Audio Classification Model - Free Detection of Scratches in Vinyl Record Audio

Is Vinyl Scratched Or Not

Developed by DunnBC22

An audio classification model fine-tuned based on wav2vec2-base, used to detect scratches in vinyl record audio.

EnglishOpen Source License:Apache-2.0 #Vinyl Record Inspection #Audio Scratch Recognition #High-Precision Classification

Downloads 22

Release Time : 1/28/2023

Model Overview

This is a binary classifier designed to predict whether scratches exist in the audio samples played from vinyl records. It achieves high accuracy and F1 scores on the evaluation dataset.

Model Features

High Accuracy

Achieves 97.52% accuracy on the evaluation dataset

Balanced Performance

F1 score reaches 96.38%, demonstrating a good balance between recall and precision

Based on wav2vec2

Leverages the powerful wav2vec2-base architecture for fine-tuning

Model Capabilities

Audio Classification

Vinyl Record Quality Inspection

Audio Anomaly Detection

Use Cases

Audio Quality Inspection

Vinyl Record Scratch Detection

Automatically detects scratches by analyzing audio played from vinyl records

Accuracy 97.52%, F1 score 96.38%

Audio Restoration

Preprocessing Filtering

Pre-identifies scratched audio requiring restoration in the audio repair workflow

🚀 wav2vec2-base-is_vinyl_scratched_or_not

This model is a fine - tuned version of facebook/wav2vec2-base on the audiofolder dataset, used for audio classification to predict whether a vinyl record is scratched.

🚀 Quick Start

This model is a fine - tuned version of facebook/wav2vec2-base on the audiofolder dataset. It achieves the following results on the evaluation set:

Loss: 0.1039
Accuracy: 0.9752
F1: 0.9638
Recall: 0.9576
Precision: 0.9700

✨ Features

This is a binary classifier that predicts whether or not the vinyl record played in the audio sample is scratched.

For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Audio-Projects/Classification/Vinyl%20Scratched%20or%20Not.ipynb

📚 Documentation

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

Training and evaluation data

Dataset Source: https://www.kaggle.com/datasets/seandaly/detecting-scratch-noise-in-vinyl-playback

🔧 Technical Details

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e - 05
train_batch_size: 32
eval_batch_size: 32
seed: 42
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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
0.6671	0.98	21	0.6235	0.6560	0.0	0.0	0.0
0.4954	1.98	42	0.2824	0.9417	0.9095	0.8517	0.9757
0.2406	2.98	63	0.1755	0.9563	0.9336	0.8941	0.9769
0.169	3.98	84	0.1545	0.9592	0.9386	0.9068	0.9727
0.1287	4.98	105	0.1249	0.9606	0.9407	0.9068	0.9772
0.1102	5.98	126	0.1159	0.9723	0.9595	0.9534	0.9657
0.0923	6.98	147	0.1073	0.9665	0.9516	0.9576	0.9456
0.0877	7.98	168	0.1039	0.9752	0.9638	0.9576	0.9700
0.0807	8.98	189	0.1088	0.9679	0.9536	0.9576	0.9496
0.0744	9.98	210	0.1041	0.9752	0.9638	0.9576	0.9700

Framework versions

Transformers 4.26.0
Pytorch 1.12.1
Datasets 2.8.0
Tokenizers 0.12.1

📄 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