Year: 2023
Type: conference-paper
Abstract: We present a first system for automatic speech recognition (ASR) for the low-resource language Luxembourgish.By applying transfer-learning, we were able to fine-tune Meta's wav2vec2-xls-r-300m checkpoint with 35 hours of labeled Luxembourgish speech data.The best word error rate received lies at 14.47.
Authors: GILLES, Peter, HOSSEINI KIVANANI, Nina, HILLAH, Léopold Edem Ayité
Institution: University of Luxembourg
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7048668308
