AI RESEARCH
A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026
arXiv CS.CL
•
ArXi:2606.03948v1 Announce Type: new We implement simultaneous translation capability with the offline direct speech-to-text translation model Canary, using the state-of-the-art policy AlignAtt, and submit it to IWSLT 2026 Simultaneous Speech Translation Shared task for Czech to English and English to German and Italian.