fx

README.md

@@ -19,19 +19,21 @@ tags:
 
 ##
 
-# Expansion of the [SHIFT TTS tool](https://github.com/audeering/shift) with [foreign langs](https://huggingface.co/dkounadis/artificial-styletts2/blob/main/Utils/all_langs.csv) and [AudioGen Soundscape](https://huggingface.co/dkounadis/artificial-styletts2/discussions/3).
+# Affective TTS / Soundscape
+
+Expansion of [SHIFT TTS tool](https://github.com/audeering/shift) with [foreign langs](https://huggingface.co/dkounadis/artificial-styletts2/blob/main/Utils/all_langs.csv) and [soundscapes via AudioGen](https://huggingface.co/dkounadis/artificial-styletts2/discussions/3).
   - Analysis of emotions of TTS [#1](https://huggingface.co/dkounadis/artificial-styletts2/discussions/2)
-  - `landscape2soundscape.py` generates soundscape, i.e. `trees, water, ..` & overlays TTS & creates video from image.
+  - Foreign languages [#4](https://huggingface.co/dkounadis/artificial-styletts2/discussions/4)
 
 ## Available Voices
 
 <a href="https://audeering.github.io/shift/">Listen to available voices!</a>
 
-## Flask API
+## Flask
 
 <details>
 <summary>
-Create virtualenv
+build virtualenv & start API
 </summary>
 
 Clone
@@ -48,14 +50,19 @@ cd artificial-styletts2/
 pip install -r requirements.txt
 ```
 
-</details>
-
-Flask API
+Flask API - start on a `tmux-session`
 
 ```
-CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=2 python api.py
+CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=0 python api.py
 ```
 
+Inference
+
+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`.
+
+</details>
+
+
 ## Landscape 2 Soundscape
 
 The following needs `api.py` to be already running on a tmux session.