audio-embedding

Pytorch port of Google Research's VGGish model used for extracting audio features.

A python library to train Deep Neural Networks on various audio tasks using Self-Supervised backbones.

Audio search using Azure Cognitive Search

🎵 专属你的私人数字调音师|AI 音乐搜索推荐 Agent | 基于大模型 + 知识图谱 + 双模型声学向量的本地智能音乐推荐系统 | LLM-powered Music Recommendation Agent with Hybrid RAG, Neo4j, and Long-term Memory

Visualizations of music semantics calculus using Spotify and deep embeddings.

Audio encoding authentication and validation library for verifying audio as being from a trusted source

SERVER: Multi-modal Speech Emotion Recognition using Transformer-based and Vision-based Embeddings

Offline AI music recommender & recogniser. Local song ID + smart playlists (CLAP + FAISS).

Extract audio embeddings from an audio file using Python

AudioMuse-AI-DCLAP is a lightweight, high-speed distilled version of LAION CLAP, designed for fast and efficient text-to-music search

🎵 AI music tagger using MusicCocoa embeddings. 163 tags across genre, mood, vocals, texture. works on CPU

Directly from voice, recognise speaker emotion, intensity, & sentiment in speaker utterances.

Generate audio embedding out of pruned L3

Audio Deep Learning Project in Java

Re-Implementation of Google Research's VGGish model used for extracting audio features using Pytorch with GPU support.

Audio Embeddings using VGGish

AudioMuse-AI-SAE implement the Sparse autoencoders (SAE) for DCLAP

Competition-winning SED (Sound Event Detection) system that identifies audio events using ML, optimized for real-world error cost reduction.

Group together similar music

Generate realistic, synthetic call center conversations