datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
SpectrogramSleepStagingDatasetmusic-tags-to-spectrogram
Dataset Card for "music-tags-to-spectrogram"
This dataset is extracted from the MTG-Jamendo Datase
We applied the following transformation:
Convert audio to spectrogram diagram.
Join tagging list into one-line text.
For example, there is a genre list that has three tags: chillout, downtempo, and easylistening.
The raw text of this example will be "chillout downtempo easylistening".
lvm_bird_spectrogramspectrogram-captionsDataset of captioned spectrograms (text describing the sound).
Amharic_Audio_and_Spectrograms
Amharic Audio Spectrogram Dataset
Dataset Info
Total samples in full dataset: 662,611
Samples in this preview: 1,000
Audio duration: 2.49 ± 1.60 seconds
Sample rate: 16kHz
Spectrogram dimensions: 80 mel bins × variable time steps
Sample Data
Audio Sample
Spectrogram
License
Apache 2.0
comp5421-mel-spectrogram-fma_small-128x216linnut_spectrogramsspectrogram_data_ultramax_music_dataset
Dataset Card for "spectrogram_data_ultramax_music_dataset"
More Information needed
linnut_spectrograms_smCREMA-mel-spectrogram-images-preprocessedspectrogramsThis dataset includes spectrograms of ~950 afrobeats songs and 1k rock songs.
The spectrograms were generated with `librosa`.bird-mel-spectrogram
Dataset Card for "mel_spectogram_bird_audio"
More Information needed
lfm-spectrogramsChirpLoc100K___A_Synthetic_Spectrogram_Dataset_for_Chirp_Localization
Dataset Card for Chirp Spectrograms
Images & Corresponding Labels for Signal Processing Research
📊 Sample Generated Spectrograms
📝 Dataset Description
This dataset contains 100,000 synthetic chirp spectrograms with corresponding labels, generated for research in signal processing and machine learning applications. The dataset is particularly useful for developing and testing models for chirp signal detection and localization.
🧑💻… See the full description on the dataset page: https://huggingface.co/datasets/nubahador/ChirpLoc100K___A_Synthetic_Spectrogram_Dataset_for_Chirp_Localization.Sound_Spectrogram
Dataset Card for "Sound_Spectrogram"
Questions about dataset
What is Spectrogram?
How were these converted to image?
Where is dataset from?
How can I use this?
More Information needed
musiccaps_spectrograms
Dataset Card for "musiccaps_spectrograms"
More Information needed
2026-06-23_verification_past_spectrogramThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6… See the full description on the dataset page: https://huggingface.co/datasets/jogarulfop/2026-06-23_verification_past_spectrogram.spectrogram_data_max_music_dataset-1
Dataset Card for "spectrogram_data_max_music_dataset-1"
More Information needed
drone-spectrogramMel_Spectrogram_Images_for_Audio_Classification
Mel-Spectrogram Image Dataset (Generated via Custom Pipeline)
> This dataset was fully generated through my notebook
> “Building an Audio Classification Pipeline with DL” available on my profile.
> It represents a complete end-to-end transformation from raw audio to clean, balanced Mel-spectrogram images suitable for deep learning.
Dataset Summary
Property
Description
Number of Classes
13 distinct audio categories
Original Audio per Class
~40 raw recordings… See the full description on the dataset page: https://huggingface.co/datasets/AIOmarRehan/Mel_Spectrogram_Images_for_Audio_Classification.CICIDS2017-Images-spectrogramsThis directory consists on 24x24 images
train folder have total 1548421 images from 10 classes
test folder have 663609 images from 10 classes
This Dataset is Spectrogram converted images using method explained in our research article XYZ.
Dataset Used: Intrusion detection evaluation dataset (CIC-IDS2017)
Image Size: 28x28
Classes:
BENIGN
Bot
DDoS
DoS GoldenEye
DoS Hulk
DoS Slowhttptest
DoS slowloris
Heartbleed
Infiltration
PortScan
License:
https://www.unb.ca/cic/datasets/ids-2017.html… See the full description on the dataset page: https://huggingface.co/datasets/rashid-rao/CICIDS2017-Images-spectrograms.CREMAD-mel-spectrogram-images-datasetSpectrograms3AudioCaps-Spectrogramsdelta_xyz_train_spectrogram_labeled_unnormalizedsoundsCaps-Spectrograms_to_Base64AudioShield_Fake_Real_Audio_Spectrogram_Datasetdrum-spectrogram-dataset
Dataset Card for "drum-spectrogram-dataset"
More Information needed
drone-spectrogram-v2spectrogram_data_Upbeat-4s
Dataset Card for "spectrogram_data_Upbeat-4s"
More Information needed