A VITS model by Rhasspy, from rhasspy/piper-voices/pl/pl_PL/darkman/medium, packaged for phoonnx, our ONNX text-to-speech library.
| Architecture | VITS |
| Upstream | rhasspy/piper-voices/pl/pl_PL/darkman/medium |
| Author | Rhasspy |
| Languages | pl-PL |
| Text input | espeak phonemes, IPA alphabet |
pip install --pre phoonnx
The phonemes come from the espeak-ng program, so install it too (for example
apt install espeak-ng). Without it, pip install --pre "phoonnx[espeak]" gives
phoonnx the espyak port of espeak-ng. Some espyak phonemes differ from those of
espeak-ng, so the voice can say some words wrong with espyak.
import wave
from phoonnx.model_manager import TTSModelManager
manager = TTSModelManager()
manager.load()
manager.merge_default_voices()
voice = manager.voices["piper/pl_PL-darkman-medium"].load()
with wave.open("output.wav", "wb") as wav_file:
text = "..." # a sentence in pl-PL
voice.synthesize_wav(text, wav_file)
In OVOS, phoonnx installs the ovos-tts-plugin-phoonnx plugin. Select the voice in mycroft.conf:
{"tts": {"module": "ovos-tts-plugin-phoonnx", "ovos-tts-plugin-phoonnx": {"voice": "piper/pl_PL-darkman-medium"}}}
phoonnx hands the text to scriptconv, our text conversion library, which normalises it and turns it into the model's input:
espeak: EspeakPhonemizer from scriptconv_copyleft.phonemizers.mul, installed by the scriptconv[espeak] extra.piper/pl_PL-darkman-mediumThe upstream declares the licence mit in the model card of rhasspy/piper-voices.