mosstts-audio_tokenizer-nano

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

Model details

Architecture	MOSS-TTS
Upstream	OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano
ONNX conversion	OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano-ONNX
Author	OpenMOSS

How to use

The phoonnx voice index does not list a voice for this model.

Licence

The upstream declares the licence apache-2.0 in the model card of OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano.

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.