JSUT
A free large-scale Japanese speech synthesis corpus with 10 hours of read speech covering all major pronunciations of daily-use Japanese kanji
Duration
10 hours
Languages
1
Sample Rate
48 kHz
Published
2017-11
Description
110 hours of read-style speech with corresponding transcriptions
2Covers all major pronunciations of daily-use Japanese kanji
3Designed for end-to-end speech synthesis systems
4Single speaker
Language Details
| Language | Duration |
|---|---|
| Japanese | 10 hours |
Publisher