Kakaru/sovits-whisper-pretrain

Model

3

stars

5

commits

1

linked in READMEs

Jun 29, 2023

updated

README

diffusion文件夹内为whisper_ppg encoder下训练到420ksteps的预训练模型

另外两个文件夹为whisper_ppg encoder下的sovits预训练模型，300ksteps为目标步数，264ksteps为loss低点，配置文件中的‘n_speakers’应修改为132

使用数据集vctk+m4singers+opencpop+kiritan

Contributors

4 commits

1 commits

Similar repos

CNChTu/Diffusion-SVC

481

ms903/Diff-SVC-refactor-pre-trained-model

13

OOPPEENN/pretrained_model

3

ChiTu/Diffusion-SVC

3

auspicious3000/contentvec

speech self-supervised representations

523

TencentGameMate/chinese_speech_pretrain

chinese speech pretrained models

1,214

fishaudio/fish-diffusion

An easy to understand TTS / SVS / SVC framework

759

fushh7/ViSpeak-Bench

0

Linked in READMEs

CNChTu/Diffusion-SVC

481

Kakaru/sovits-whisper-pretrain

Model

3

stars

5

commits

1

linked in READMEs

Jun 29, 2023

updated

README

diffusion文件夹内为whisper_ppg encoder下训练到420ksteps的预训练模型

另外两个文件夹为whisper_ppg encoder下的sovits预训练模型，300ksteps为目标步数，264ksteps为loss低点，配置文件中的‘n_speakers’应修改为132

使用数据集vctk+m4singers+opencpop+kiritan

Similar repos

CNChTu/Diffusion-SVC

481

ms903/Diff-SVC-refactor-pre-trained-model

13

OOPPEENN/pretrained_model

3

ChiTu/Diffusion-SVC

3

auspicious3000/contentvec

speech self-supervised representations

523

TencentGameMate/chinese_speech_pretrain

chinese speech pretrained models

1,214

fishaudio/fish-diffusion

An easy to understand TTS / SVS / SVC framework

759

fushh7/ViSpeak-Bench

0

Linked in READMEs

CNChTu/Diffusion-SVC

481

Contributors

4 commits

1 commits