librosa-audio
CommunityExtract music features and find similar tracks.
Education & Research#recommendation#similarity search#knn#mfcc#music information retrieval#librosa#audio feature extraction
Authorxjtulyc
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Turn raw audio files into reliable musical fingerprints by extracting tempo, chroma, MFCCs, spectral descriptors, and pitch, so you can analyze tracks or search for similar songs.
Core Features & Use Cases
- End-to-end MIR feature extraction: Load music, compute beat/tempo, chroma, MFCCs (including deltas), spectral features, onset detection, and pitch statistics into one consistent vector per track.
- Corpus-level similarity search: Build a feature dataset for a music folder and retrieve the k most similar tracks to a query using feature scaling and nearest-neighbor search.
- Audio analysis workflows: Use features for playlist generation, music recommendation prototyping, music dataset exploration, and creating training inputs for downstream ML tasks.
Quick Start
Use the librosa-audio skill to find the 5 most similar tracks in a music corpus to an attached query file.
Dependency Matrix
Required Modules
librosanumpyscipyscikit-learnpandassoundfilepyarrow
Components
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: librosa-audio Download link: https://github.com/xjtulyc/awesome-rosetta-skills/archive/main.zip#librosa-audio Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.