Description
I did this model in a particual way, I used a 10 second dataset on XTyde2, this sort of TTS with even little dataset. Then I created 10 or more TTS audios and mixed them creating a 1 minute dataset. I did it, and I'm surprised. It's not perfect, bur it sounds a little like him. Credit: @FanFierik @ANGETYDE [IT/ENG] (for XTyde2) <
Comments
No comments yet. Start the conversation!
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
![Disney FastPlay Guy [Latin Spanish]](https://imgproxy.weights.com/insecure/size:860:0/resizing_type:fill/plain/https://assets.weights.com/clm72tkjh0rnpcctcosqwgm1d/9894c378e421fa93010ac56c96840696.png)
