VoiceCloning
1.0.0
提出YourTTS模型的論文用作API的中央構建塊。 Yourtts用於零擊的多語言方法,可用於多語言音頻數據,同時構建較舊的Vits方法。
| 模型 | URL |
|---|---|
| 揚聲器編碼器 | 關聯 |
| Exp1。 Yourtts-en(VCTK) | 關聯 |
| EXP1。 Yourtts-en(VCTK) + SCL | 關聯 |
| Exp2。 Yourtts-en(VCTK)-pt | 關聯 |
| Exp2。 Yourtts-en(VCTK)-PT + SCL | 關聯 |
| EXP3。 Yourtts-en(VCTK)-pt-fr | 關聯 |
| EXP3。 Yourtts-en(VCTK)-PT-FR SCL | 關聯 |
| EXP4。 Yourtts-en(VCTK+libritts)-pt-fr SCL | 關聯 |
MOS的音頻在這裡可用。另外,音頻在這裡。
庫(測試清潔):1188,1995,260,1284,2300,237,908,1580,121和1089
VCTK:P261,P225,P294,P347,P238,P234,P248,P335,P245,P245,P326和P302
MLS葡萄牙語:12710,5677,12249,12287,9351,11995,7925,7925,3050,4367和1306
@ARTICLE{2021arXiv211202418C,
author = {{Casanova}, Edresson and {Weber}, Julian and {Shulby}, Christopher and {Junior}, Arnaldo Candido and {G{"o}lge}, Eren and {Antonelli Ponti}, Moacir},
title = "{YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone}",
journal = {arXiv e-prints},
keywords = {Computer Science - Sound, Computer Science - Computation and Language, Electrical Engineering and Systems Science - Audio and Speech Processing},
year = 2021,
month = dec,
eid = {arXiv:2112.02418},
pages = {arXiv:2112.02418},
archivePrefix = {arXiv},
eprint = {2112.02418},
primaryClass = {cs.SD},
adsurl = {https://ui.adsabs.harvard.edu/abs/2021arXiv211202418C},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}