how-to

There are 2 posts filed in how-to (this is page 1 of 1).

Using Google Speech API to transcribe interviews

What do London, Madrid, Seoul, Tel Aviv, Warsaw and São Paulo have in common?

They are the cities where Google has set up a Google Campus!

I recently checked in for a series of presentations. And the first one blew my mind.

Onome Ofoman, a “googler” from New York, demoed a couple of Machine Learning tricks, including speech to text conversion (or speech recognition, or automatic transcription) in a few terminal commands!

So when I went back home that evening, I spent a couple of hours figuring out how the Google Cloud Platform works, set up an account, and very quickly got a result with a recording I had just done!


Continue reading →

Scorsese now has a Brazilian clone

or: Cloning Scorsese, the technical part

The ACMI Labs team has recently released on Github the code for the “Scorsese” audio guide web app. They are based in Melbourne, Australia, but this is important for museums all around the world.

In short: thanks to Scorsese and the ACMI team, any museum can now publish a mobile-accessible-user-friendly audio guide, using simple open source tools.

So, practically? How do you do it?

Here’s what we’ve just done for a Brazilian institution (in portuguese):
https://vilaitororo.github.io/bemvindos/

5: Vila Itororó today. 9: Francisco de Castro, who built Vila Itororó. 10: The swimming pool in 1929.
5: Vila Itororó today. 9: Francisco de Castro, who built Vila Itororó. 10: The swimming pool in 1929.

Continue reading →