Competitions &
benchmarks
Prize competitions
Compete for prizes by building models on novel datasets hosted by the Mozilla Data Collective.
Lost In Transcription: Advancing Speech Recognition for Underserved Linguistic Contexts
This competition evaluates performance on real-world bilingual dialogues in Indonesian-Javanese, Nahuatl-Spanish, and Spanish-English.
544 joined
$20,000
in prizes
2 days left
About us
Mozilla Data Collective is a mission-locked British company, incubated by Mozilla Foundation and backed by the not-for-profit Mozilla.org.
We are the collective of technologists, linguists, researchers and creatives who want AI to be all it promises to be - not all it threatens to be.
Whether you're a tech start up, library, archive, or global non-profit, we want to enable you to share your datasets in line with your mission and values.
