This repository holds the finetuned weights for Tortoise v2 for the LJSpeech voice. It is a good demonstration of how powerful fine-tuning Tortoise can be.
Usage:
- Clone Tortoise, jbetker/tortoise-tts-v2 or https://github.com/neonbjb/tortoise-tts
- Clone this repo to download weights
- Run any Tortoise script with the flag
--model_dir=<path_to_where_you_cloned_this_repo>/modelsand--voice=lj - For fine-tuned models, I recommend using the
high_qualitypreset. Faster rendering modes can exhibit artifacts in the output.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.