WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words
Lukas Wolf, Klemen Kotar, Greta Tuckute, Eghbal A. Hosseini, Tamar I. Regev, Ethan Wilcox, Alexander Scott Warstadt · 2023
Lukas Wolf, Klemen Kotar, Greta Tuckute, Eghbal Hosseini, Tamar I. Regev, Ethan Gotlieb Wilcox, Alexander Scott Warstadt. Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning. 2023.