Skip to content

A Python library for classifying vinyl record condition using deep learning models.

License

Notifications You must be signed in to change notification settings

jvaleroliet/deepdiggin

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

deepdiggin

Introduction

This project aims to construct a simple python library to classify vinyl records according to the Goldmine Grading.

The package is constructed with my finetuned version of facebook/wav2vec2-base called wav2vec2-base-vinyl_condition.

Features

  • Obtain grading condition from an audio clip of the vinyl.

Future features:

  • Improve model accuracy.
  • Obtain visual grading condition from a photo of the vinyl.
  • Obtain visual grading condition of the cover from a photo of it.
  • Process entire folders creating a dataframe with paths and conditions.
  • Find out wherever a vinyl is scratched or not.
  • Determine the genre of the vinyl.
  • Identification of vinyl from photo.
  • Get value of the record based on discogs price.

Installation

To install, run the following command in your terminal:

pip install git+https://github.com/jvaleroliet/deepdiggin.git@main

Basic Usage

from  deepdiggin import predict

condition = predict.condition_from_audio('path/to/audio')

print(condition)

Under Construction

The package is under construction. Feel free to collaborate. 🎵

About

A Python library for classifying vinyl record condition using deep learning models.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages