I'm still figuring out what to do with Bendroid..

Daisy, give me your answer

"Put on your Sunday Clothes" sung by Vocaloid Leon.

Lyrics:
Put on your Sunday clothes there's lots of world out there
Get out the Brilliantine and dime cigars
We're gonna find adventure in the evening air
Girls in white in a perfumed night where the lights are bright as the stars

Put on your Sunday clothes we're gonna ride through town
In one of those new horsedrawn open cars
We'll see the show at Delmonico's and we'll close the town in a whirl
And we won't come come until we've kissed a girl


Put on your Sunday Clothes

Gumi singing meow meow meow meow meow meow i am a cat meow meow i am a cat, known from this weird Internet video: https://www.youtube.com/watch?v=g1Og5Tg_Jyo

meow meow i am a cat — gumi english vocaloid

El Cumbanchero

Mr. Robot, Tetris, 2nd Waltz, Greensleeves, M'lady's Ride, Pop Goes the Weasel, Waves of the Danube, Adieu and Raveleijn

This Is My New Favorite Instrument

I played this on my laptop keyboard using Musical Typing in GarageBand.

The Sims on my laptop keyboard

I trained a neural network on cover of the song Hide and Seek by Imogen Heap using an implementation of Google's WaveNet. It had been training for 6000 steps.

If you have any suggestions on what I should train a model next, please let me know!

Here's the TensorFlow implementation of WaveNet that I used:
https://github.com/ibab/tensorflow-wavenet

And here's the cover song that I trained it on:
https://soundcloud.com/sango312/hide-and-seek-neko-kanochi

I trained WaveNet on Hide and Seek

I trained Google's WaveNet on the sound of an opera singer singing opera.  

These are 24 samples, each generated at a later time, with more learning steps passed. Unfortunately, I forgot to log how many steps were done at each sample point, but the total amount of steps is 34,895.

Here's the TensorFlow implementation of WaveNet that I used:
https://github.com/ibab/tensorflow-wavenet

Benimation

Popular tracks