styletts2-hitz-eu-styletts2

A StyleTTS2 model by HiTZ Center, from HiTZ/StyleTTS2-eu, packaged for phoonnx, our ONNX text-to-speech library.

Model details

Architecture	StyleTTS2
Upstream	HiTZ/StyleTTS2-eu
Author	HiTZ Center
Languages	eu-ES
Text input	ahotts phonemes, IPA alphabet

How to use

pip install --pre phoonnx "scriptconv[eu]"

import wave
from phoonnx.model_manager import TTSModelManager

manager = TTSModelManager()
manager.load()
manager.merge_default_voices()

voice = manager.voices["hitz/eu-antton"].load()

with wave.open("output.wav", "wb") as wav_file:
    text = "..."  # a sentence in eu-ES
    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": "hitz/eu-antton"}}}

Text front end

phoonnx hands the text to scriptconv, our text conversion library, which normalises it and turns it into the model's input:

• ahotts: AhoTTSPhonemizer from scriptconv.phonemizers.eu, installed by the scriptconv[eu] extra.

phoonnx voices

• hitz/eu-antton
• hitz/eu-maider

Licence

The upstream declares the licence apache-2.0 in the model card of HiTZ/StyleTTS2-eu.

The licence notes for this model:

| HiTZ Basque StyleTTS2 (base + emotion) | hitz-eu-styletts2/*, hitz-eu-emo-styletts2/* | Apache-2.0 |

Related projects

• phoonnx: runs this model, in Python and in OVOS.
• scriptconv: text normalisation, script conversion and phonemizers for phoonnx.
• The StyleTTS2 collection: every StyleTTS2 model packaged for phoonnx.