format

README.md

@@ -28,7 +28,13 @@ Expansion of [SHIFT TTS tool](https://github.com/audeering/shift) with [AudioGen
 
 <a href="https://audeering.github.io/shift/">Listen to available voices!</a> & <a href="https://huggingface.co/dkounadis/artificial-styletts2/blob/main/Utils/all_langs.csv">Foreign languages</a>
 
-## Flask
+[TTS Demo](https://huggingface.co/dkounadis/artificial-styletts2/blob/main/demo.py) saves `demo.wav`
+
+```python
+CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=0 python demo.py
+```
+
+## API
 
 <details>
 <summary>
@@ -55,14 +61,7 @@ Flask `tmux-session`
 CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=0 python api.py
 ```
 
-# Demo
-
-```python
-# saves demo.wav
-CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=0 python demo.py
-```
-
-# Inference
+# Inference via API
 
 Following examples need `api.py` to be running. [Set this IP](https://huggingface.co/dkounadis/artificial-styletts2/blob/main/tts.py#L85) to the IP shown when starting `api.py`.