vits-hf_community_owensong_inflect-nano-v2-onnx

A VITS model by owensong, from owensong/inflect-nano-v2-onnx, packaged for phoonnx, our ONNX text-to-speech library.

Model details

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["inflect/nano-en"].load()

with wave.open("output.wav", "wb") as wav_file:
    text = "..."  # a sentence in en-us
    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": "inflect/nano-en"}}}

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

• inflect/nano-en

Licence

The upstream declares the licence apache-2.0 in the model card of owensong/inflect-nano-v2-onnx.

Related projects

• phoonnx: runs this model, in Python and in OVOS.
• scriptconv: text normalisation, script conversion and phonemizers for phoonnx.
• phoonnx.js: runs VITS voices with espeak or unicode input in the browser; live demo at tigregotico.pt/demo.
• The VITS collection: every VITS model packaged for phoonnx.