coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
TTS/recipes/thorsten_DE
History
Eren Gölge 9e5a469c64
d-vector handling (#1945) 
* Update BaseDatasetConfig

- Add dataset_name
- Chane name to formatter_name

* Update compute_embedding

- Allow entering dataset by args
- Use released model by default
- Use the new key format

* Update loading

* Update recipes

* Update other dep code

* Update tests

* Fixup

* Load multiple embedding files

* Fix argument names in dep code

* Update docs

* Fix argument name

* Fix linter
 		2022-09-13 14:10:33 +02:00
..
align_tts d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
glow_tts d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
hifigan Training recipes for thorsten dataset (#1020) 2022-05-30 12:07:31 +02:00
multiband_melgan Training recipes for thorsten dataset (#1020) 2022-05-30 12:07:31 +02:00
speedy_speech d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
tacotron2-DDC d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
univnet Training recipes for thorsten dataset (#1020) 2022-05-30 12:07:31 +02:00
vits_tts d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
wavegrad Training recipes for thorsten dataset (#1020) 2022-05-30 12:07:31 +02:00
wavernn Training recipes for thorsten dataset (#1020) 2022-05-30 12:07:31 +02:00
README.md Training recipes for thorsten dataset (#1020) 2022-05-30 12:07:31 +02:00
download_thorsten_DE.sh Training recipes for thorsten dataset (#1020) 2022-05-30 12:07:31 +02:00

README.md

🐸💬 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
```

💡 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 💪.