At Twine, we specialize in helping AI companies create high-quality custom audio and video AI datasets.
During conversations with clients, we often get asked if there are any off-the-shelf audio and video datasets we would recommend, for testing and for them to use as a point of comparison with custom approaches.
When we started searching for lists of datasets it was very surprising how limited they were.
To address this, we have put together a list of 100+ open audio and video datasets. The datasets listed below all contain the number of recordings in each dataset, the number of participants involved, the languages of the speech content, the file size, and file type.
We have also put together an Airtable of this dataset list so that you can easily search, filter, edit and export it yourself. Please click the link below if you would like to access it:
Access the searchable AI Datasets table
| Urban Sound 8K dataset |
| No. Recordings: 8732 File Size: 13.84KB Filetype: .WAV/.CSV Language(s): US English Description: Contains Urban sounds from 10 classes like an air conditioner, dog bark, drilling, siren, street music, etc. https://urbansounddataset.weebly.com/urbansound8k.html |
|
Mozilla Common Voice |
| No. Recordings: 75,879 File Size: 63Gb Filetype: MP3 Language(s): US English Description: An open-source, multi-language dataset of voices that anyone can use to train speech-enabled applications. https://commonvoice.mozilla.org/en/datasets |
|
HiEve |
| No. Recordings: 1,000,000 Filetype: MP4 Language(s): US English Description: The largest collection of poses which focuses on very challenging and realistic tasks of human-centric analysis in various crowds & complex events, including subway getting on/off, collision, fighting, and earthquake escape http://humaninevents.org/ |
To continue reading this article, click here.
