First test of the new Tortoise model. 4 voices, which also can be found in the YourTTS model I posted recently. LJS, John, and Tom rendered without any stammers or repeats, Lah has some stutters if I recall. No cherry-picked examples. Gen settings same as in my Tortoise fine tuning video, except denoise set to 256 (richer sounding voices).
“LJSpeech” voice https://youtu.be/MdzuEeVY3Ak?t=0
“John” voice https://youtu.be/MdzuEeVY3Ak?t=236
“Lah” voice https://youtu.be/MdzuEeVY3Ak?t=471
“Tom” voice https://youtu.be/MdzuEeVY3Ak?t=698
1 epoch base language training, 2 epochs fine-tuning
Download on Huggingface:
https://huggingface.co/AOLCDROM/Tortoise-TTS-MSFT-VCTK-4V-En
Speech is from “The Great Dictator”. Full text can be found here to read along if you like:
https://www.charliechaplin.com/en/films/7-The-Great-Dictator/articles/29-The-Final-Speech-from-The-Great-Dictator-