Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/alanjumeaucourt/hitorflop
Language modele that detect if a song include potential "caracteristic" of a HIT / top song
https://github.com/alanjumeaucourt/hitorflop
ai cnn docker docker-compose nextjs python
Last synced: 10 days ago
JSON representation
Language modele that detect if a song include potential "caracteristic" of a HIT / top song
- Host: GitHub
- URL: https://github.com/alanjumeaucourt/hitorflop
- Owner: AlanJumeaucourt
- Created: 2023-11-15T01:59:38.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2024-11-09T18:49:54.000Z (11 days ago)
- Last Synced: 2024-11-09T19:35:11.462Z (11 days ago)
- Topics: ai, cnn, docker, docker-compose, nextjs, python
- Language: TypeScript
- Homepage: https://hitorflop.myfunnycluster.dynamic-dns.net/
- Size: 350 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
Awesome Lists containing this project
README
# Hit or Flop 🎵
A production-ready AI system that uses convolutional neural networks to predict whether a song has the characteristics of a hit or a flop.
## 🚀 Features
- Real-time song prediction using Spotify's track data
- Interactive web interface
- Integration with Spotify's API
- Containerized application using Docker
- Neural network model trained on historical hit data## 🔍 How It Works
The system analyzes various musical features of a track (such as danceability, energy, tempo, etc.) using Spotify's audio features API and processes them through our trained neural network to predict its hit potential.
## 🎯 Demo
### Homepage
![Homepage](homepage.png)## 🛠️ Tech Stack
- **Frontend**: React, TypeScript, Tailwind CSS
- **Backend**: Python, FastAPI
- **AI Model**: TensorFlow, Keras
- **Infrastructure**: Docker, Docker Compose## 📝 Model Training
The neural network model was trained using a comprehensive dataset of historical music data. You can find the training notebook and methodology on Kaggle:
[Spotify Hit or Flop Training Notebook](https://www.kaggle.com/code/alanjumeaucourt/spotify-hit-or-flop)## 🚀 Getting Started
1. Clone the repository
2. Create a `.env` file with your Spotify API credentials
3. Run with Docker Compose: