Peter Lustig

Create

Peter Lustig

Other LanguagesNarrativeOld ManGerman
Rubbel Katz user image
Rubbel Katz
1 year ago
👀

127

👍

2

🪄

51

Description

Host of an eighties childrens educational show called "Löwenzahn" (Dandelion). Sweet gramps storytelling voice slightly scratchy. Trained with German dataset (Larger/broader dataset+Premium mode training)

Comments

J B user image
J B
1 year ago

Yoo, this is insanely good

J B user image
J B
1 year ago

how many epochs / how long was the audio sample you trained it with?

Rubbel Katz user image
Rubbel Katz
1 year ago

Sorry for the late reply I didn't get a notification that someone commented on this model. ~ I don't know exactly - the training page doesn't display the filenames correctly they get truncated. Thus I can't verify it with my dataset. Strange enough the training page also lists ALL uploaded dataset files from the model history. But I can say that I nearly filled up the maximum dataset length for premium accounts. Audio in the training dataset is pretty clear and noise free. Its interesting to see that the resulting model is also able to churn out some singing even though it was only trained on speech. ~~~~~~Edit: I must add, that I manually removed all problematic sections in the dataset (music and sound bleed throughs). Not sure if I catched them all. :P

Add a comment

Samples

New
Classic
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English

Pitch

More to explore

Loading more

Selected Audio
Selected Audio