[CODE] Pretrained models for ZMM-TTS

This repository contains pretrained models for our paper submitted to IEEE/ACM TASLP: "ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations" Cheng Gong, Xin Wang, Erica Cooper, Dan Wells, Longbiao Wang, Jianwu Dang, Korin Richmond, Junichi Yamagishi Preprint: https://arxiv.org/abs/2312.14398 Please cite this paper if you use this work. Code and instructions for using these pretrained models can be found here: https://github.com/nii-yamagishilab/ZMM-TTS See that codebase's README for more information about dependencies etc. Files `output_letovec`, `output_xptovec_wo`, and `output_xptovec` are part of the `txt2vec` model and should go together in a subdirectory of that name. These models were trained using data from the MLS (https://www.openslr.org/94/) and NHT Swedish (https://huggingface.co/datasets/jimregan/nst_swedish_tts) datasets. COPYING This pretrained model is licensed under the Creative Commons License: Attribution 4.0 International http://creativecommons.org/licenses/by/4.0/legalcode Please see `LICENSE.txt` for the terms and conditions of this pretrained model. ACKNOWLEDGMENTS This work was supported in part by the National Natural Science Foundation of China under Grant 62176182, the China Scholarship Council (CSC) No. 202206250146, MEXT KAKENHI Grants (21H04906, 21K17775, 21K11951), and the National Research Council of Canada’s Ideation Fund: ‘Small teams – Big Ideas’.

Gong, C., Wang, X., Cooper, E., Wells, D., Wang, L., Dang, J., Richmond, K., & Yamagishi, J. (2024). Pretrained models for ZMM-TTS. Zenodo. https://doi.org/10.5281/zenodo.10784364