Tundragoon/Kokoro-German

Kokoro-German ist ein TTS-Modell mit 82 Millionen Parametern. Das Modell verwendet denselben Inferenzcode wie Kokoro.

Warning:

The model has been trained on limited data and still lacks training.

🐈 GitHub: https://github.com/Thomcle/kokoro_german

Usage

!pip install -q kokoro>=0.9.2 soundfile
!apt-get -qq -y install espeak-ng > /dev/null 2>&1
!git clone https://github.com/Thomcle/kokoro_german kokoro_german
from kokoro_german.kokoro import KPipeline
from IPython.display import display, Audio
import soundfile as sf
import torch
pipeline = KPipeline(lang_code='d')
text = '''
Kokoro-German ist ein TTS-Modell mit 82 Millionen Parametern.
Das Modell verwendet denselben Inferenzcode wie Kokoro.
'''
generator = pipeline(text, voice='df_eva')
for i, (gs, ps, audio) in enumerate(generator):
    print(i, gs, ps)
    display(Audio(data=audio, rate=24000, autoplay=i==0))
    sf.write(f'{i}.wav', audio, 24000)

Training data

To train this model, we used the HUI-Audio-Corpus-German dataset:

Speaker:

• bernd
• eva

Acknowledgements

I would like to thank Tundrag, creator of webaudio, for funding this project!

@yl4579 for architecting StyleTTS 2.

@rzvzn for coding Kokoro.

Licence

The model is licensed under Apache 2.0, making commercial use accessible.