Views
No views yet
manifest/utils is used to extract speaker embedding, generate manifest, and apply vocoder.manifest/arctic* provides the pre-trained vocoder for each speaker.speecht5_vc.pt are reimplemented Voice Conversion fine-tuning on the released manifest but with a smaller batch size or max updates (Ensure the manifest is ok).samples are created by the released fine-tuned model and vocoder.1@inproceedings{ao-etal-2022-speecht5,
2 title = {{S}peech{T}5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing},
3 author = {Ao, Junyi and Wang, Rui and Zhou, Long and Wang, Chengyi and Ren, Shuo and Wu, Yu and Liu, Shujie and Ko, Tom and Li, Qing and Zhang, Yu and Wei, Zhihua and Qian, Yao and Li, Jinyu and Wei, Furu},
4 booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
5 month = {May},
6 year = {2022},
7 pages={5723--5738},
8}