Text-to-Speech2019en

CSTR VCTK Corpus

Speech data from 110 English speakers with various accents. Used for multi-speaker TTS.

Metrics:mos, sim-score
Paper / WebsiteDownload

No benchmark results indexed for this dataset yet.

Contribute results on GitHub

Other Text-to-Speech Datasets

LJ Speech
VCTK Benchmark - Text-to-Speech | CodeSOTA