Hlavní stránka > Výsledky hledání: keywords:"masked language modeling"
Hledej:
Tipy pro vyhledávaní :: Rozšířené hledání
Hledej ve sbírkách:
Seřadit podle: Zobrazit výsledky: Výstupní formát:
Národní úložiště šedé literatury Nalezeno 2 záznamů.  Hledání trvalo 0.01 vteřin. 
Large Language Models in Speech Recognition
 Tomašovič, Martin ; Polok, Alexander (oponent) ; Beneš, Karel (vedoucí práce)
This thesis explores the conditions under which a Large Language Model (LLM) improves Automatic Speech Recognition (ASR) transcription. Specifically, the thesis focuses on n-best rescoring with masked and autoregressive language models. The n-best hypotheses are scored using LLM and then this score is interpolated with the scores from ASR. This approach is tested across different ASR settings and datasets. Results demonstrate that rescoring hypotheses from Wav2Vec 2.0 and Jasper ASR systems reduces the error rate. LLM fine-tuning proves to be very beneficial. Smaller fine-tuned models can surpass larger non-fine-tuned ones. The findings of this thesis broaden the knowledge of the conditions for LLM (autoregressive, masked) utilization in ASR rescoring. The thesis observes the influence of fine-tuning, normalization and separating scores from a CTC decoder on the decrease of word error rate.
Úplný záznam
Document Information Extraction
 Janík, Roman ; Špaňhel, Jakub (oponent) ; Hradiš, Michal (vedoucí práce)
With development of digitization comes the need for historical document analysis. Named Entity Recognition is an important task for Information extraction and Data mining. The goal of this thesis is to develop a system for extraction of information from Czech historical documents, such as newspapers, chronicles and registry books. An information extraction system was designed, the input of which is scanned historical documents processed by the OCR algorithm. The system is based on a modified RoBERTa model. The extraction of information from Czech historical documents brings challenges in the form of the need for a suitable corpus for historical Czech. The corpora Czech Named Entity Corpus (CNEC) and Czech Historical Named Entity Corpus (CHNEC) were used to train the system, together with my own created corpus. The system achieves 88.85 F1 score on CNEC and 87.19 F1 score on CHNEC, obtaining new state-of-the-art results.
Úplný záznam

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.
Digitální repozitář :: Hledej :: Nový záznam :: Personalizace :: Nápověda
Powered by Invenio v1.1.2
Spravuje admin.invenio@techlib.cz
Tato stránka je dostupná také v následujících jazycích:
Česky  English