will opensource training dataset?

[lucasjinreal]

will opensource training dataset?

[MaxMax2016]

will opensource training dataset?

[JohnsonTsing]

Dear All, we have just upload our paper to arxiv: https://arxiv.org/abs/2203.16922

As stated in the paper, we have used two datasets: (1) one large homegrown dataset from Peoples' Daily corpus; (2) the other is the small public TTS dataset from Databaker.

The 2nd dataset is already open-sourced, and is publicly available. Sorry, for the present, the 1st dataset is not open-sourced.

Anyway, we will release the pretrained model soon.

[valleysprings]

where is the link of the second dataset