glowtts-nl-rdh

A Glow-TTS model by Rhasspy, from github.com/rhasspy/larynx/releases/download/v1.0/nl_rdh-glow_tts.tar.gz, packaged for phoonnx, our ONNX text-to-speech library.

Model details

Architecture	Glow-TTS
Upstream	github.com/rhasspy/larynx/releases/download/v1.0/nl_rdh-glow_tts.tar.gz
Author	Rhasspy
Languages	nl
Text input	gruut phonemes, IPA alphabet
Vocoder	vocoders-larynx-hifigan-vctk-small

How to use

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

import wave
from phoonnx.model_manager import TTSModelManager

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

voice = manager.voices["larynx/nl-rdh-glow_tts"].load()

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

The model makes a spectrogram, and the vocoder in Model details turns it into audio. phoonnx downloads the vocoder with the voice.

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": "larynx/nl-rdh-glow_tts"}}}

Text front end

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

• gruut: GruutPhonemizer from scriptconv.phonemizers.mul, installed by the scriptconv[gruut] extra.

phoonnx voices

• larynx/nl-rdh-glow_tts

Licence

No licence is recorded for this model. Check the upstream release before you use it.

Related projects

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