Use of Large Language Models to improve Speech-to-text output (LLM4STT)
The project aims to find out how large language models (LLMs) can be used to to improve the transcription of audio into text (Speech-to-Text, STT). To this end analyse the quality and reliability of this approach.
Key data
Projectlead
Katsiaryna Mlynchyk
Deputy Projectlead
Project partners
SpinningBytes AG
Project status
completed, 12/2024 - 01/2026
Institute/Centre
Centre for Artificial Intelligence (CAI)
Funding partner
SpinningBytes AG
Project budget
20'000 CHF