Fine tuned from Cori-
Cori is a single speaker voice trained from 24 hours of Librivox recordings for 640 epochs by Bryce Beattie.
The checkpoint can be found here:
https://huggingface.co/datasets/rhasspy/piper-checkpoints/tree/main/en/en_GB/coriAudio was sourced from 2 Librivox Readers, all Librivox Recordings are in the public domain.
Data includes 45 minutes from speaker B, and 2.5 hours from Speaker A.
Speaker A data can be found:
https://archive.org/details/josh-leach
Speaker B data can be found:
https://archive.org/details/howard-skymanI place no additional restrictions on this voice.
