Coqui TTS - Max (Luxembourgish Male Voice)
A VITS-based text-to-speech model for Luxembourgish, featuring a natural male voice.
Model Description
This model was trained using the Coqui TTS framework on Luxembourgish speech data from the Lëtzebuerger Online Dictionnaire (LOD) example sentences.
"Max" is a male Luxembourgish voice based on recordings from a real speaker.
Model Details
- Architecture: VITS
- Language: Luxembourgish (lb)
- Speaker: Single speaker (male)
- Sample Rate: 22050 Hz
- Checkpoint: 50,000 steps
- License: CC BY-NC 4.0 (Non-commercial use only)
License Notice
This model is for non-commercial use only. All commercial uses are prohibited. The voice data is derived from recordings of a real speaker and may only be used freely for non-commercial purposes.
Usage
Note: Text should be lowercased before synthesis. Additional text normalization may be required.
import torch
import scipy.io.wavfile as wavfile
from TTS.utils.synthesizer import Synthesizer
# Load the model
synthesizer = Synthesizer(
tts_checkpoint="path/to/coqui-tts-max.pth",
tts_config_path="path/to/config.json",
use_cuda=torch.cuda.is_available()
)
# Generate speech
wav = synthesizer.tts("moien, wéi geet et dir?")
# Save to file
wavfile.write("output.wav", 22050, wav)
Technical Specifications
| Parameter | Value |
|---|---|
| Hidden Channels | 192 |
| Text Encoder Layers | 6 |
| Posterior Encoder Layers | 16 |
| Flow Layers | 4 |
| Mel Channels | 80 |
| FFT Size | 1024 |
Citation
If you use this model, please cite:
@misc{zls2025coquimax,
title={Coqui TTS Max - Luxembourgish Male Voice},
author={Zenter fir d'Lëtzebuerger Sprooch},
year={2025},
publisher={Hugging Face},
url={https://huggingface.co/ZLSCompLing/CoquiTTS-Max}
}
Acknowledgments
Originally trained by Marco Barnig. Now developed and maintained by Zenter fir d'Lëtzebuerger Sprooch.
Voice data sourced from the Lëtzebuerger Online Dictionnaire (LOD). The original audio files are available via the LOD linguistic data on data.public.lu, which provides an XML file containing example sentence IDs. Audio files can be accessed at:
https://lod.lu/uploads/examples/AAC/{folder}/{id}.m4a
where {folder} is the first 2 characters of {id}.
This model is used in Sproochmaschinn, a Luxembourgish speech processing platform.