CoolFace
Apppublic

juliensimon/song-lyrics

sourceHugging Faceupdated 6mo agoView on Hugging Face
12likes
App README

Song Lyrics Genre Classifier

Paste song lyrics and predict their musical genre using a fine-tuned transformer model. Returns the top 3 most likely genres with confidence scores.

<p align="center"> <img src="https://img.shields.io/badge/Task-Text%20Classification-blue" alt="Text Classification"> <img src="https://img.shields.io/badge/Training-AutoNLP-green" alt="AutoNLP"> <img src="https://img.shields.io/badge/SDK-Gradio-orange" alt="Gradio"> </p>

How It Works

  1. 1.Paste song lyrics into the text box
  2. 2.The model analyzes vocabulary, themes, and writing style
  3. 3.Get the top 3 predicted genres with confidence percentages

Example output: "These lyrics are 72.34% Rock, 15.21% Pop and 8.45% Country."

Model

DetailValue
Modeljuliensimon/autonlp-song-lyrics-18753417
ArchitectureAutoModelForSequenceClassification
TrainingHugging Face AutoNLP
Datasetjuliensimon/autonlp-data-song-lyrics
TaskMulti-class text classification

Tech Stack

  • —Transformers: Sequence classification with softmax scoring
  • —PyTorch: Inference backend
  • —Gradio: Web interface

Run Locally

bash
git clone https://huggingface.co/spaces/juliensimon/song-lyrics
cd song-lyrics
pip install -r requirements.txt
python app.py