YourTTS training datasets and fine-tuning

[CuCl-2]

I would like to ask which datasets were used to train the checkpoint
tts_models/multilingual/multi-dataset/your_tts.

In addition, how can this checkpoint be fine-tuned?
Specifically, I am not referring to single-speaker fine-tuning, but rather to fine-tuning the model on the Emilia dataset.

[eginhard]

You can find the YourTTS paper here, where the training datasets are listed.

For fine-tuning, you can adapt this recipe: https://github.com/idiap/coqui-ai-TTS/blob/dev/recipes/multilingual/cml_yourtts/train_yourtts.py (that one is originally for a different YourTTS model, but it should need only minor changes).