| --- |
| language: |
| - lb |
| tags: |
| - text-to-speech |
| - fish-speech |
| - luxembourgish |
| - tts |
| license: cc-by-nc-sa-4.0 |
| datasets: |
| - denZLS/Luxembourgish-Male-TTS-for-LOD |
| base_model: fishaudio/openaudio-s1-mini |
| --- |
| |
| # Fish Speech - Luxembourgish TTS |
|
|
| Fine-tuned [Fish Speech](https://github.com/fishaudio/fish-speech) Dual-AR model for Luxembourgish text-to-speech. |
|
|
| ## Model Details |
|
|
| - **Base Model:** [fishaudio/openaudio-s1-mini](https://huggingface.co/fishaudio/openaudio-s1-mini) |
| - **Architecture:** Dual-AR Transformer (860M parameters) |
| - **Language:** Luxembourgish (lb) |
| - **Training Data:** 32,000 samples from male Luxembourgish speaker |
| - **Training Steps:** 9,000 steps (~2.4 epochs) |
| - **Fine-tuned on:** NVIDIA RTX 5090 |
|
|
| ## Usage |
|
|
| Requires [Fish Speech](https://github.com/fishaudio/fish-speech) installed. |
|
|
| ```bash |
| # WebUI |
| python tools/run_webui.py \ |
| --llama-checkpoint-path vivienhenz/fish-speech-luxembourgish \ |
| --decoder-checkpoint-path fishaudio/openaudio-s1-mini/codec.pth |
| ``` |
|
|
| ## Training Details |
|
|
| - Dataset: 32,000 male voice samples (~28 hours) |
| - Optimizer: AdamW (lr=1e-4) |
| - Precision: bf16-mixed |
| - Training time: ~3 hours on RTX 5090 |
|
|
| ## Example |
|
|
| Input: `d'nottär huet haut de mueren zwou venten.` |
|
|
| Output: Natural Luxembourgish male voice |
|
|
| ## License |
|
|
| CC-BY-NC-SA-4.0 (inherited from Fish Speech) |
|
|
