artificialguybr's picture
Upload 650 files
45ee559
|
raw
history blame
872 Bytes

๐Ÿธ๐Ÿ’ฌ TTS Thorsten Recipes

For running the recipes you need the Thorsten-Voice dataset.

You can download it manually from the official website or use download_thorsten_de.sh alternatively running any of the train_modelX.pyscripts will download the dataset if not already present.

Then, go to your desired model folder and run the training.

Running Python files. (Choose the desired GPU ID for your run and set ```CUDA_VISIBLE_DEVICES```)
```terminal
CUDA_VISIBLE_DEVICES="0" python train_modelX.py
```

๐Ÿ’ก Note that these runs are just templates to help you start training your first model. They are not optimized for the best result. Double-check the configurations and feel free to share your experiments to find better parameters together ๐Ÿ’ช.