Résumé abstractif à partir d'une transcription audio

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Derkach, Ilia
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915245773029376
author Derkach, Ilia
author_facet Derkach, Ilia
contents Currently, large language models are gaining popularity, their achievements are used in many areas, ranging from text translation to generating answers to queries. However, the main problem with these new machine learning algorithms is that training such models requires large computing resources that only large IT companies have. To avoid this problem, a number of methods (LoRA, quantization) have been proposed so that existing models can be effectively fine-tuned for specific tasks. In this paper, we propose an E2E (end to end) audio summarization model using these techniques. In addition, this paper examines the effectiveness of these approaches to the problem under consideration and draws conclusions about the applicability of these methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11803
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Résumé abstractif à partir d'une transcription audio
Derkach, Ilia
Information Retrieval
Currently, large language models are gaining popularity, their achievements are used in many areas, ranging from text translation to generating answers to queries. However, the main problem with these new machine learning algorithms is that training such models requires large computing resources that only large IT companies have. To avoid this problem, a number of methods (LoRA, quantization) have been proposed so that existing models can be effectively fine-tuned for specific tasks. In this paper, we propose an E2E (end to end) audio summarization model using these techniques. In addition, this paper examines the effectiveness of these approaches to the problem under consideration and draws conclusions about the applicability of these methods.
title Résumé abstractif à partir d'une transcription audio
topic Information Retrieval
url https://arxiv.org/abs/2504.11803