LJSpeech
Single-speaker English read speech TTS dataset with 24 hours of recordings, one of the most widely used TTS benchmarks
Duration
24 hours
Languages
1
Sample Rate
22.05 kHz
Published
2017-07
Description
1Single female speaker reading audiobook recordings
2Sourced from the LibriVox project
3Contains 13,100 audio clips
4CC0 1.0 public domain license
5One of the most widely used benchmark datasets in TTS
Language Details
| Language | Duration |
|---|---|
| English | 24 hours |
Publisher