Modelpublic

Pendrokar/xvapitch_expresso

sourceHugging Facecc-by-nc-4.0updated 1y agoView on Hugging Face

1likes

Model Card

xVASynth's xVAPitch (v3) type of voice models based on the Expresso dataset. Without enunciated, laughing, whispering and singing styles. From the confused style, only questions were used.

These models can also do emphasis on words by using colons :, rather than the typical quotemarks " which are skipped by the xVASynth text pre-processor:

—What :exactly: is it?
—Well :normally: we just let it run.

ex01 male: <audio controls> <source src="https://huggingface.co/Pendrokar/xvapitchexpresso/resolve/main/xex01.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio>

ex02 female: <audio controls> <source src="https://huggingface.co/Pendrokar/xvapitchexpresso/resolve/main/xex02.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio>

ex03 male: <audio controls> <source src="https://huggingface.co/Pendrokar/xvapitchexpresso/resolve/main/xex03.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio>

ex04 female: <audio controls> <source src="https://huggingface.co/Pendrokar/xvapitchexpresso/resolve/main/xex04.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio> (These audio samples were created with the xVASynth Editor with the SR option (44kHz), not xVATrainer whose automatically created samples often sound different)

Legal note: Although these datasets are licensed as CC BY 4.0, the base v3 model that these models are fine-tuned from, was pre-trained on non-permissive data.

v3 base model: https://huggingface.co/Pendrokar/xvapitch