GenreClassifier

GenreClassifier

Guesses the music genre of an uploaded audio track with an LSTM model trained on the GTZAN dataset. For music fans and students who want to try a small audio classifier.

Made by Enutrof on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: GenreClassifier guesses the music genre of a track you upload. It was trained on the GTZAN dataset, which covers ten genres, using an LSTM model built with Keras on a TensorFlow backend. It runs as a Gradio app.

Who it suits: It suits music fans, students and developers who want to see a small audio classification model in action.

Industry | Who uses it | How they use it | Example
Music | Hobbyists and DJs | Get a quick genre guess for a track | Upload a song and read the predicted genre
Education | Students | Study audio classification with an LSTM | Try tracks from different genres
Machine learning | Developers | Look at a small Keras audio model in an app | Call its API from a script

You can skip it if you need reliable tagging of music unlike the training data.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Your own computer, running Python 3.10 on Windows, macOS or Linux
• Your own scripts, through the API the README points to

Use case | Who | What they get back
Guess a genre | Music fans | A predicted genre for an uploaded track
Test on your own music | Students | A feel for how the model copes with unfamiliar songs
Call it from code | Developers | Predictions through the Space's API

How to set it up:

• Nothing to install if you use the Space online
• Python 3.10, if you run a copy on your own computer
• The Python packages in requirements.txt

1. Open the Space's page on Hugging Face to use it online.
2. To run a copy, install huggingface_hub and download the Space into a folder.
3. Move into that folder and install the pinned Gradio version, then the listed packages.
4. Start the app with Python.

pip install -U huggingface_hub
hf download Enutrof/GenreClassifier --repo-type space --local-dir GenreClassifier
cd GenreClassifier
pip install gradio==6.30.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space and upload an audio track. The app returns its genre prediction. The README also points to API documentation for the Space if you want to call it from code. On your own copy, start the app with this command and open the local page Gradio prints.

python app.py

Example: Upload a song you know well, such as a jazz or rock track. You get back the genre the model thinks it is, which you can compare with your own idea.

For newcomers and experts: If you are new, upload a track and see which genre it names. Then try a few songs from different styles to see where it goes wrong.

If you know the field, the model is an LSTM built with Keras on TensorFlow and trained on GTZAN, which holds 100 tracks of 30 seconds for each of ten genres. The author says it does well on GTZAN-like data and would do better with more data. Expect weaker results on music unlike that set.

You upload an audio track
The app prepares the audio for the model
The LSTM scores the ten genres
The page shows the predicted genre

Good to know:

• License: afl-3
• Cost to run: none named. The online Space runs on Hugging Face.
• Data it reaches: the audio you upload, and the saved model file in its repository.
• Limits: the model learned from 100 tracks per genre, so unusual or mixed-genre songs may be misjudged.

On Hugging Face, 13 November 2026

• Likes: 3
• Built with: gradio
• License: afl-3.0

Links

• Space: https://huggingface.co/spaces/Enutrof/GenreClassifier
• Files: https://huggingface.co/spaces/Enutrof/GenreClassifier/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.