Thorsten (neutral): Difference between revisions

From Voice Technology Wiki
Jump to navigation Jump to search
m (test edit)
m (Thorsten moved page Dataset: Thorsten (neutral) to Thorsten (neutral) over redirect: Moved to main namespace)
(No difference)

Revision as of 11:43, 26 December 2021


Thorsten (neutral)
Language German
Link https://github.com/thorstenMueller/deep-learning-german-tts
Filesize 3GB
Speaker number 1
Number recordings 23000
Average phrase length 53 chars
License


General info on dataset

A german single male speaker dataset.

Recording quality

Recordings is mixed quality. First x recordings has some random noise. Check this csv file for a list of qualities of recordings. test3