NVIDIA's multilingual speech dataset Granary-v2 trends on Hugging Face
nvidia · hf · 2026-10-30
NVIDIA's Granary-v2 dataset is trending on Hugging Face. It covers automatic speech recognition, translation, audio-text-to-text and question answering tasks, spanning a wide range of languages including Arabic, Bulgarian, Bengali, Czech and Danish — a large-scale multilingual speech understanding resource.
More from Multimodal
- AI-generated pulp-noir illustration series nails red-and-black thriller aesthetics — LudovicCreator · 2026-10-30
- One Month of Work: Creator Releases Episode 1 of AI-Generated Dark Fantasy Series — Helen-2006 · 2026-10-30
- Oxford's Holo4D uses holistic 4D reconstruction as geometric control for video diffusion — Oxford · 2026-10-30
- 100% AI-made short film reimagines ancient Egypt with BMX bikes, full 5-step workflow shared — socialwithaayan · 2026-10-30
- 90 open-source apps in two weeks: the full #OpenSourceHiggsfield community catalogue — Visual_Tiger_2400 · 2026-10-30
- OpenSuperComputer open-sources a Higgsfield-style automated content generation pipeline — iAM_A_NiceGuy · 2026-10-30