README.md

metadata

license: mit
datasets:
  - seungheondoh/LP-MusicCaps-MSD
  - seungheondoh/LP-MusicCaps-MC
language:
  - en
metrics:
  - bleu
  - bertscore
tags:
  - music
  - music-captioning

• Repository: LP-MusicCaps repository
• Paper: ArXiv

:sound: LP-MusicCaps: LLM-Based Pseudo Music Captioning

This is a implementation of LP-MusicCaps: LLM-Based Pseudo Music Captioning. This project aims to generate captions for music. 1) Tag-to-Caption: Using existing tags, We leverage the power of OpenAI's GPT-3.5 Turbo API to generate high-quality and contextually relevant captions based on music tag. 2) Audio-to-Caption: Using music-audio and pseudo caption pairs, we train a cross-model encoder-decoder model for end-to-end music captioning

LP-MusicCaps: LLM-Based Pseudo Music Captioning
SeungHeon Doh, Keunwoo Choi, Jongpil Lee, Juhan Nam
To appear ISMIR 2023

TL;DR

• 1.Tag-to-Caption: LLM Captioning: Generate caption from given tag input.
• 2.Pretrain Music Captioning Model: Generate pseudo caption from given audio.
• 3.Transfer Music Captioning Model: Generate human level caption from given audio.

Open Source Material

• pre-trained models
• music-pseudo caption dataset
• demo

are available online for future research. example of dataset in notebook