Join Coding Elite (get early access to new videos and projects of mine, and request for my models to try a new text/song): http://codingelite.com/join
This video is for entertainment purposes only and no disrespect is intended towards Jordan Peterson. This model was trained using an implementation of the papers "Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis" (https://arxiv.org/abs/1803.09017) and "Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron" (https://arxiv.org/abs/1803.09047), using about 6 hours of clear Jordan Peterson audio. Given a reference audio, this model will synthesise speech in that particular style. The model architecture is different to my previous first attempt at doing something like this (https://www.youtube.com/watch?v=3rgAV...), and I definitely feel this one is far better as the audio is far clearer (no singing-into-a-fan type background noise).