---
title: Demo Lux Piper Tts
emoji: 🌖
colorFrom: pink
colorTo: blue
sdk: gradio
sdk_version: 4.36.1
app_file: app.py
pinned: false
license: cc-by-nc-sa-4.0
---

# Luxembourgish Text-to-Speech Synthesizer

This is a text-to-speech synthesizer that uses the Piper TTS model to synthesize Luxembourgish text into speech. The project includes a Gradio interface that allows users to enter Luxembourgish text and hear the synthesized speech.


## Demo

You can try out the demo of this project on Hugging Face Spaces [here](https://huggingface.co/spaces/sekhan/demo-lux-piper-tts).

## Usage

To use the project, simply enter some Luxembourgish text into the input field and click the "Synthesize" button to hear the synthesized speech.

## Files

The project includes the following files:

- `app.py`: the main Python script that contains the code for the Gradio interface and the text-to-speech synthesizer.
- `requirements.txt`: a list of the necessary libraries and their versions.
- `.gitignore`: a file that excludes certain files and directories from being tracked by Git.
- `lu_rtl_high3000.onnx` and `lu_rtl_high3000.onnx.json`: the Piper TTS model and configuration files for Luxembourgish.

## License

This project is licensed under the Creative Commons Attribution Non Commercial Share Alike 4.0 License.

## Acknowledgements

The Luxembourgish voice is trained using the subset: `rtl.lu : 1257 luxembourgish male samples (© RTL-CLT-UFA)` subset of the dataset by `mbarnig/lb-de-fr-en-pt-12800-TTS-CORPUS`.


## Disclaimer

This project is a demo and is not intended for production use. The text data entered into the interface is not saved and is only used for the speech synthesis.