---
language:
- en
---


To run this model, you need to follow the XTTS inference code, with documentation [here](https://tts.readthedocs.io/en/latest/models/xtts.html#training).

It was finetuned on the "Joe Pera talks you to sleep" video. A sample of produced speech will be provided.

A training log is included.

The speech is enhanced with the Adobe Podcast service (where the 85p indicates the extent to which the output is enhanced).