shami-apc

A Shami model by Tushe, from Tushe/shami-tts, packaged for phoonnx, our ONNX text-to-speech library.

Model details

Architecture	Shami
Upstream	Tushe/shami-tts
Author	Tushe
Languages	apc
Text input	shami phonemes, IPA alphabet

How to use

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

import wave
from phoonnx.model_manager import TTSModelManager

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

voice = manager.voices["Tushe/shami-tts"].load()

with wave.open("output.wav", "wb") as wav_file:
    text = "..."  # a sentence in apc
    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": "Tushe/shami-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:

• shami: ShamiPhonemizer from scriptconv.phonemizers.shami, installed by the scriptconv[shami] extra.

phoonnx voices

• Tushe/shami-tts

Licence

The upstream declares the licence cc-by-nc-4.0 in the model card of Tushe/shami-tts.

Related projects

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