dkounadis/artificial-styletts2

Affective TTS / Soundscape

Expansion of SHIFT TTS tool with AudioGen soundscapes

• Analysis of emotions of TTS
• Listen also foreign languages

Available Voices

Native English! / Non-native English accents! / Foreign languages

TTS Demo

API

Build virtualenv & start API

Clone

git clone https://huggingface.co./dkounadis/artificial-styletts2

Install

virtualenv --python=python3 ~/.envs/.my_env
source ~/.envs/.my_env/bin/activate
cd artificial-styletts2/
pip install -r requirements.txt

Flask tmux-session

CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=0 python api.py

Inference via API

Following examples need api.py to be running. Set this IP to the IP shown when starting api.py.

Landscape 2 Soundscape

The following needs api.py to be already running on a tmux session.

# TTS & soundscape - overlay to .mp4
python landscape2soundscape.py

For SHIFT demo / Collaboration with SMB

• YouTube Videos

SoundScape Live (iterative) Demo - Paplay

Special Flask API for playing sounds live

CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=/data/dkounadis/.hf7/ CUDA_VISIBLE_DEVICES=4 python live_api.py

Client - Describe any sound with words and it will be played back to you.

python live_demo.py  # will ask text input & play soundscape

SoundScape (basic) Demo

CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=/data/dkounadis/.hf7/ CUDA_VISIBLE_DEVICES=4 python demo.py

Audiobook

Create audiobook from .docx. Listen to it - YouTube male voice / female voice

# generated audiobook will be saved in ./tts_audiobooks
python audiobook.py