Would it be possible to use sherpa-onnx to do voice conversion? (Changing voice in audio to something else)
And maybe voice cloning for tts? (Clone voice from audio and generate new speech with that voice)?
Like the project Applio does, I think it's based on vits
Would it be possible to use sherpa-onnx to do voice conversion? (Changing voice in audio to something else) And maybe voice cloning for tts? (Clone voice from audio and generate new speech with that voice)?
Like the project Applio does, I think it's based on vits