Audio samples generated by the code in the keithito/tacotron repo.

• Samples on the left are from a model trained for 441K steps on the LJ Speech Dataset.
• Samples on the right are from a model trained by @MXGray for 140K steps on the Nancy Corpus.
• None of these sentences were part of either training set.

Scientists at the CERN laboratory say they have discovered a new particle.

There’s a way to measure the acute emotional intelligence that has never gone out of style.

President Trump met with other leaders at the Group of 20 conference.

The Senate’s bill to repeal and replace the Affordable Care Act is now imperiled.

Generative adversarial network or variational auto-encoder.

The buses aren't the problem, they actually provide a solution.