@inproceedings{sharipov-ortega-machacek-2026-pocket,
    title = "A Pocket Offline Model for Simultaneous Speech Translation as {CUNI} Submission to {IWSLT} 2026",
    author = "Sharipov Ortega, Aziz  and
      Mach{\'a}{\v{c}}ek, Dominik",
    editor = "Salesky, Elizabeth  and
      Anastasopoulos, Antonios  and
      Negri, Matteo  and
      Federico, Marcello",
    booktitle = "Proceedings of the 23rd International Conference on Spoken Language Translation ({IWSLT} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, USA (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/bulk-corrections-2026-07-02/2026.iwslt-1.22/",
    doi = "10.18653/v1/2026.iwslt-1.22",
    pages = "197--203",
    ISBN = "979-8-89176-411-8",
    abstract = "We implement a direct speech translation model Canary for simultaneous translation with AlignAtt simultaneous policy. We focus on Nemo toolkit with the recent state-of-the-art foundation model Canary-1B-v2 that has only one billion of parameters, which is suitable for small pocket devices. This is a CUNI submission to IWSLT 2026 Simultaneous Speech Translation Shared task on Czech to English and English to German and Italian."
}