Edit model card

Lyrics Genre Classification Model

Description

The model was trained using the BERT language model on my song lyrics dataset to predict the genre of a given song based on its lyrics. This repository houses the machine learning model, which is capable of making predictions in four distinct genres: Pop, Rock, Hip-Hop and Arabesk. For training and test codes check out Github page.

Dataset

The model was trained on a diverse and labeled dataset of song lyrics, which contained 3172 rows. The dataset was carefully curated to include songs from a wide range of artists and genres, ensuring a comprehensive representation of Pop, Rock, Hip-Hop and Arabesk music. DATASET

Quick Start

from transformers import pipeline

classifier = pipeline("text-classification", model="Veucci/lyrics-to-genre")
result = classifier("Bedava yaşıyoruz, dostlar bedava Hava bedava, bulut bedava Dere tepe bedava, yağmur çamur bedava")

print(result)

License

This dataset is released under the Creative Commons Attribution-NonCommercial license. This means that you are not allowed to use the dataset for commercial purposes. For detailed information about the license, please refer to the LICENSE file.

Contact

If you have any questions, suggestions, or concerns regarding this dataset, please feel free to reach out to email at efe.ozkan732@gmail.com. I hope this model helps in your genre classification tasks and inspires further exploration of song lyrics analysis!

Downloads last month
28
Safetensors
Model size
109M params
Tensor type
I64
·
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Veucci/turkish-lyric-to-genre

Space using Veucci/turkish-lyric-to-genre 1