Do the synthesize inputs must be the .npy file

[wpy0521]

as i known, Clarinet is a end-to-end model(Text-to-Speech). But this model allows only the .npy file as the inputs. Can anyone use a sentence to synthesize ?
what's more , i wonder the function of the Clarinet. can it realize the multi-speakers synthetise? or just make synthesize results better?

[BABALA258]

same question. The LJspeechDataset and DataLoader only load the .npy data as inputs, not use the sentence text.

[mingboma]

same question here as well. Is there a way that I could use text as input?