|
--- |
|
license: mit |
|
base_model: |
|
- coqui/XTTS-v2 |
|
tags: |
|
- death |
|
datasets: |
|
- drewThomasson/Death_from_puss_and_boots |
|
language: |
|
- en |
|
--- |
|
|
|
|
|
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/66903a229152b56774988b49/mqi8FWsLfOih5uSETbjjT.jpeg) |
|
|
|
|
|
Trained on this video https://www.youtube.com/watch?v=6d6H9n2CVzw |
|
|
|
Use V2 as its the best version of this, it doesn't hallucinate as much lol |
|
|
|
I've included the model files and the best .wav file to use as the base sample when using the model on xtts |
|
|
|
|
|
Compatable with ebook2audiobookxtts --> |
|
https://github.com/DrewThomasson/ebook2audiobookXTTS |
|
|
|
This model is based on xtts v2 which cannot be used commercially as per the [xtts license which is in a limbo state](https://github.com/coqui-ai/TTS/issues/3490) |