@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharipov-ortega-machacek-2026-pocket">
<titleInfo>
<title>A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aziz</namePart>
<namePart type="family">Sharipov Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Macháček</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-411-8</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">sharipov-ortega-machacek-2026-pocket</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.22/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>197</start>
<end>203</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026
%A Sharipov Ortega, Aziz
%A Macháček, Dominik
%Y Salesky, Elizabeth
%Y Anastasopoulos, Antonios
%Y Negri, Matteo
%Y Federico, Marcello
%S Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA (in-person and online)
%@ 979-8-89176-411-8
%F sharipov-ortega-machacek-2026-pocket
%X 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.
%U https://aclanthology.org/2026.iwslt-1.22/
%P 197-203
Markdown (Informal)
[A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026](https://aclanthology.org/2026.iwslt-1.22/) (Sharipov Ortega & Macháček, IWSLT 2026)
ACL