ibab / tensorflow-wavenet

A TensorFlow implementation of DeepMind's WaveNet paper
MIT License
5.42k stars 1.29k forks source link

WaveNet launches in the Google Assistant #296

Open Zeta36 opened 7 years ago

Zeta36 commented 7 years ago

https://deepmind.com/blog/wavenet-launches-google-assistant/

The new, improved WaveNet model still generates a raw waveform but at speeds 1,000 times faster than the original model, meaning it requires just 50 milliseconds to create one second of speech. In fact, the model is not just quicker, but also higher-fidelity, capable of creating waveforms with 24,000 samples a second. We have also increased the resolution of each sample from 8 bits to 16 bits, the same resolution used in compact discs.

It is also now capable of running at scale and is the first product to launch on Google’s latest TPU cloud infrastructure.

lef-fan commented 7 years ago

waiting for it !!!

weixsong commented 7 years ago

not sure how they made the inference so fast, maybe a more simple model is used, together with TPU. Wait for their detailed paper.