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 isn't deployed by any Inference Provider. 🙋 Ask for provider support