| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
Release Vevo1.5 and Training Code of Vevo (#426) | 1 年前 | |
Support Multi-speaker VITS (#131) Support Multi-speaker VITS & Hi-Fi TTS dataset preprocessing | 2 年前 | |
Evaluation refactor (#117) An overall refactor to the Amphion Evaluation module for faster inference speed and more computational modes for compatibility | 2 年前 | |
Release Vevo1.5 and Training Code of Vevo (#426) | 1 年前 | |
Fix typos in config files for TTA (#163) Co-authored-by: VocodexElysium <vocodexelysium@gmail.com> | 2 年前 | |
Release DualCodec and DualCodec-VALLE. Remove previous valle_v2 model in favor of new models. (#443) * add dualcodec code * update amphion readme of dualcodec * update amphion readme * readme * remove valle_v2 infavor of dualcodec-valle * readme * format codes * remove chinese characters in dualcodec * add amphion license | 1 年前 | |
Release Vevo1.5 and Training Code of Vevo (#426) | 1 年前 | |
Update Info of SingVisio (#274) Update Info of SingVisio citation, resources links, and Emilia TODOs | 1 年前 | |
Release Vevo1.5 and Training Code of Vevo (#426) | 1 年前 |