@inproceedings{luu-bojar-2025-cuni,
    title = "{CUNI}-{NL}@{IWSLT} 2025: End-to-end Offline Speech Translation and Instruction Following with {LLM}s",
    author = "Luu, Nam  and
      Bojar, Ond{\v{r}}ej",
    editor = "Salesky, Elizabeth  and
      Federico, Marcello  and
      Anastasopoulos, Antonis",
    booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.iwslt-1.28/",
    doi = "10.18653/v1/2025.iwslt-1.28",
    pages = "282--288",
    ISBN = "979-8-89176-272-5",
    abstract = "This paper describes the CUNI-NL team{'}s submission to the IWSLT 2025 Offline Speech Translation and Instruction Following tasks, focusing on transcribing the English audio, and translating the English audio to German text. Our systems follow the end-to-end approach, where each system consists of a pretrained, frozen speech encoder, along with a medium-sized large language model fine-tuned with LoRA on three tasks: 1) transcribing the English audio; 2) directly translating the English audio to German text; and 3) a combination of the above two tasks, i.e. simultaneously transcribing the English audio and translating the English audio to German text."
}