nateraw/download-musiccaps-dataset

Download the MusicCaps dataset for music captioning

115

stars

12

commits

Jupyter Notebook

primary language

May 19, 2026

updated

README

download-musiccaps-dataset

Download the MusicCaps dataset for music captioning.

👀 Try it in Colab + Explore the Samples 👉

Setup

Requires datasets[audio], ffmpeg, yt-dlp, torchaudio.

Contributors

12 commits

Similar repos

google/MusicCaps

152

mulab-mir/song-describer-dataset

The Song Describer dataset is an evaluation dataset made of ~1.1k captions for 706 permissively…

177

AMAAI-Lab/MidiCaps

A large-scale dataset of caption-annotated MIDI files.

86

amaai-lab/MidiCaps

57

jako4295/j2a

A Multimodal Large Language Model for Music Captioning

2

cdjkim/audiocaps

🔊 Repository for our NAACL-HLT 2019 paper: AudioCaps

216

MTG/mtg-jamendo-dataset

Metadata, scripts and baselines for the MTG-Jamendo dataset

406

OpenSound/AudioCaps

26

Languages

Jupyter Notebook

76.1%

Python

23.9%

nateraw/download-musiccaps-dataset

Download the MusicCaps dataset for music captioning

115

stars

12

commits

Jupyter Notebook

primary language

May 19, 2026

updated

README

download-musiccaps-dataset

Download the MusicCaps dataset for music captioning.

👀 Try it in Colab + Explore the Samples 👉

Setup

Requires datasets[audio], ffmpeg, yt-dlp, torchaudio.

Similar repos

google/MusicCaps

152

mulab-mir/song-describer-dataset

The Song Describer dataset is an evaluation dataset made of ~1.1k captions for 706 permissively…

177

AMAAI-Lab/MidiCaps

A large-scale dataset of caption-annotated MIDI files.

86

amaai-lab/MidiCaps

57

jako4295/j2a

A Multimodal Large Language Model for Music Captioning

2

cdjkim/audiocaps

🔊 Repository for our NAACL-HLT 2019 paper: AudioCaps

216

MTG/mtg-jamendo-dataset

Metadata, scripts and baselines for the MTG-Jamendo dataset

406

OpenSound/AudioCaps

26

Contributors

12 commits

Languages

Jupyter Notebook

76.1%

Python

23.9%