vits-hitz-gl_sabela

A VITS model by HiTZ Center, from HiTZ/TTS-gl_sabela, packaged for phoonnx, our ONNX text-to-speech library.

Model details

Architecture	VITS
Upstream	HiTZ/TTS-gl_sabela
Author	HiTZ Center
Languages	gl-ES
Text input	cotovia phonemes, cotovia alphabet

How to use

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

import wave
from phoonnx.model_manager import TTSModelManager

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

voice = manager.voices["hitz/gl_sabela-vits"].load()

with wave.open("output.wav", "wb") as wav_file:
    text = "..."  # a sentence in gl-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/gl_sabela-vits"}}}

Text front end

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

• cotovia: CotoviaPhonemizer from scriptconv.phonemizers.gl, installed by the scriptconv[gl] extra.

phoonnx voices

• hitz/gl_sabela-vits

Licence

The upstream declares the licence apache-2.0 in the model card of HiTZ/TTS-gl_sabela.

Related projects

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