styletts2-ca-bsc_lt

A StyleTTS2 model by BSC-LT, from BSC-LT/styletts2-catalan-multispeaker, packaged for phoonnx, our ONNX text-to-speech library.

Model details

Architecture	StyleTTS2
Upstream	BSC-LT/styletts2-catalan-multispeaker
Author	BSC-LT
Languages	ca
Text input	espeak phonemes, IPA alphabet

How to use

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["bsc/ca-bet"].load()

with wave.open("output.wav", "wb") as wav_file:
    text = "..."  # a sentence in ca
    voice.synthesize_wav(text, wav_file)

The voice clones a speaker from reference audio; the phoonnx README shows how to pass it.

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": "bsc/ca-bet"}}}

Text front end

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.phonemizers.mul, installed by the scriptconv[espeak] extra.

phoonnx voices

• bsc/ca-bet
• bsc/ca-eli
• bsc/ca-eva
• bsc/ca-jan
• bsc/ca-mar
• bsc/ca-ona
• bsc/ca-pau
• bsc/ca-pep
• bsc/ca-pol
• bsc/ca-styletts2
• bsc/ca-teo
• bsc/ca-uri

Licence

The upstream declares the licence gpl-3.0 in the model card of BSC-LT/styletts2-catalan-multispeaker.

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.