mosstts-multi-openmoss_team-nano_100m

A MOSS-TTS model by OpenMOSS, from OpenMOSS-Team/MOSS-TTS-Nano-100M, packaged for phoonnx, our ONNX text-to-speech library.

Model details

Architecture	MOSS-TTS
Upstream	OpenMOSS-Team/MOSS-TTS-Nano-100M
ONNX conversion	OpenMOSS-Team/MOSS-TTS-Nano-100M-ONNX
Author	OpenMOSS
Languages	ar, cs, da, de, el, en, es, fa, fr, hu, it, ja, ko, pl, pt, ru, sv, tr, zh
Text input	Unicode codepoints of the text

How to use

pip install --pre phoonnx

import wave
from phoonnx.model_manager import TTSModelManager

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

voice = manager.voices["mosstts/nano/ar"].load()

with wave.open("output.wav", "wb") as wav_file:
    text = "..."  # a sentence in ar
    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": "mosstts/nano/ar"}}}

Text front end

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

• unicode: UnicodeCodepointPhonemizer from scriptconv.phonemizers.base, in scriptconv itself.

phoonnx voices

• mosstts/nano/ar
• mosstts/nano/cs
• mosstts/nano/da
• mosstts/nano/de
• mosstts/nano/el
• mosstts/nano/en
• mosstts/nano/es
• mosstts/nano/fa
• mosstts/nano/fr
• mosstts/nano/hu
• mosstts/nano/it
• mosstts/nano/ja
• mosstts/nano/ko
• mosstts/nano/pl
• mosstts/nano/pt
• mosstts/nano/ru
• mosstts/nano/sv
• mosstts/nano/tr
• mosstts/nano/zh

Licence

The upstream declares the licence apache-2.0 in the model card of OpenMOSS-Team/MOSS-TTS-Nano-100M.

Related projects

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