# WebUI
python tools/run_webui.py \
    --llama-checkpoint-path vivienhenz/fish-speech-luxembourgish \
    --decoder-checkpoint-path fishaudio/openaudio-s1-mini/codec.pth

Training Details

Base Model: <a href="https://huggingface.co/fishaudio/openaudio-s1-mini" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">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

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)