Deep learning based content moderation from text, audio, video & image input modalities.

Recognizing the genre of music files using machine learning and deep learning models

Genre Classification using Convolutional Neural Networks

공개 한국어 감성 검색 엔진 - 2017 제 11회 공개SW개발자대회 결선작

🎵 Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis

🎵 Trained CNN model for Genre classification on GTZAN dataset [CNN Model: https://github.com/Hguimaraes/gtzan.keras]

Generate vector embeddings for music

Data pipeline and training pipeline for 🎵 music genre classification from FMA dataset

Categorize audio files by genre effortlessly. Use Dockerized environment and API to classify music genres.

Genre Classification Model Based on VGGish

The project consists in evaluating music similarity and building a genre classifier using song embeddings from GTZAN dataset extracted with Essentia’s MSD-MusiCNN model.

musical genres binary classification using pytorch.audio and keras

This is Content based music recommendation system. I have used both audio features and lyrics (text based) features for recommending most similar songs to a given query song.

to classify music into different genres

beets plugin to auto-detect the genre for each item within your music library

This is a site (or a component of the project Cine Sprite) which provides simple yet pleasing interface with filters of genre selection and many more. Developed by Pirate-Emperor, Cine_Sprite_Genre is a web application inspired by Netflix, but with a specific focus on movie genre selection.

This project uses LLMs to generate music from text by understanding prompts, creating lyrics, determining genre, and composing melodies. It harnesses LLM capabilities to create songs based on text inputs through a multi-step approach.

Developed by Pirate-Emperor, Cine_Sprite_Genre is a web application inspired by Netflix, but with a specific focus on movie genre selection and also on other aspects of an OTT site.

A PySpark MLlib classification model to classify songs based on a number of characteristics into a set of 23 electronic genres.