VITS
Collection
VITS voices in ONNX for phoonnx: Piper, MMS, Coqui VITS and VITS2, one voice per repo. โข 1,581 items โข Updated
A VITS model by Meta, from facebook/mms-tts-evn, packaged for phoonnx, our ONNX text-to-speech library.
| Architecture | VITS |
| Upstream | facebook/mms-tts-evn |
| ONNX conversion | willwade/mms-tts-multilingual-models-onnx/evn |
| Author | Meta |
| Languages | evn |
| Text input | characters of the text |
pip install --pre phoonnx
import wave
from phoonnx.model_manager import TTSModelManager
manager = TTSModelManager()
manager.load()
manager.merge_default_voices()
voice = manager.voices["facebook/mms-tts-evn-Evenki"].load()
with wave.open("output.wav", "wb") as wav_file:
text = "..." # a sentence in evn
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": "facebook/mms-tts-evn-Evenki"}}}
phoonnx hands the text to scriptconv, our text conversion library, which normalises it and turns it into the model's input:
graphemes: GraphemePhonemizer from scriptconv.phonemizers.base, in scriptconv itself.facebook/mms-tts-evn-EvenkiThe upstream declares the licence cc-by-nc-4.0 in the model card of facebook/mms-tts-evn.