blackbartblues/piper-pl-bass
By blackbartblues · ↓ 14 · ♥ 0 · Updated 2026-03-02
What's in this repo
This page lists the files in blackbartblues/piper-pl-bass, including bass.onnx, diuna.onnx.
- 2 ONNX models (.onnx files)
- 9 files, including 3 .json, 2 .onnx, 1 .md, 1 .ckpt, 1 .yaml
- Last updated 2026-03-02
ONNX files
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
Piper TTS — Bass (pl_PL)
Polski model TTS oparty na architekturze VITS (Piper TTS), fine-tuned na polskich nagraniach mowy.
Pliki modelu
| Plik | Opis |
|---|---|
bass.onnx |
Model inference (ONNX, 61 MB) |
bass.onnx.json |
Konfiguracja modelu |
epoch=5999-step=1541560.ckpt |
Checkpoint PyTorch Lightning (do dalszego treningu) |
Parametry treningu
- Jakość: medium (22050 Hz, 256 filtrów)
- Epoki: 6000 (fine-tuning od pl_PL-darkman-medium)
- Dataset: ~10 000 segmentów polskiej mowy
- GPU: AMD RX 9070 XT (ROCm 7.2)
- Framework: PyTorch 2.10 + PyTorch Lightning
Użycie z Piper
# Instalacja
pip install piper-tts
# Synteza
echo "Życie musi trwać." | piper \
--model bass.onnx \
--output_file output.wav
Użycie z Home Assistant (Wyoming TTS)
Skopiuj bass.onnx i bass.onnx.json do katalogu modeli Piper w Home Assistant.
Użycie z Python
from piper import PiperVoice
voice = PiperVoice.load("bass.onnx", config_path="bass.onnx.json")
with open("output.wav", "wb") as f:
voice.synthesize("Witaj świecie!", f)
Licencja
Model bazowy (darkman_medium): Apache 2.0.
Model info
Created: 2026-03-01
Updated: 2026-03-02
View on Hugging Face