This repository accompanies the research paper Visatronic: A Multimodal Decoder-Only Model for Speech Synthesis by Gupta, Akshita, and Likhomanenko, Tatiana and Yang, Karren, and Bai, He and Aldeneh, ...
This decoder supports both baseline (sequential) and progressive JPEG images. The decoder was made for the purpose of learning how JPEG images work, and I am making it available so it may help others ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback