English | 简体中文

DiffSVCBaseModel

A Diff-SVC base model for all kind of voice

Have a preview~

Raw	Inference with Nahida model
Raw	Result

How to use?

1. Choose and download this model

2. Fill your config and put your datasets into (diffsvc-root)/data/raw/{speaker_name}/

3. Throw this base model(only .ckpt file) into (diffsvc-root)/checkpoints/{speaker_name}

4. Then start preprocessing and training as usual

How much data do you use?

I use 2 public datasets(opencpop ,m4singer),40h+ audio in total.

I want to train my own base model!

OK, you can download this bianry file.

Download

** Please choose a model that matches your config.yaml or config_nsf.yaml **

Version	URL	Reference value of lr
384rc,50k_step	Click here	0.0016
384rc,80k_step	Click here	0.0032
384rc,100k_step	Click here	0.0032

rc: residual_channels

More coming soon...

Repos

Repo	URL
Diff-SVC	Click here
44.1KHz Vocoder	Click here
M4Singer	Click here
OpenCPOP	Click here
Pre-trained_Models(My friend's pre-trained model)	Click here