Developer Attempts to Transcribe a Podcast with Microsoft's Speech API. Hilarity Ensues.

Over the last few years, the wave of Machine Learning and Artificial Intelligence APIs has been cresting as more and more businesses see the potential for differentiation and more and more API providers look to service that need. IBM clearly recognized the potential of these APIs when it acquired AlchemyAPI back in 2015. Alchemy specialized in machine-learning driven APIs like sentiment analysis and image/language processing. Those APIs are now a part of IBM’s Watson portfolio. 

Now, a few years later, everyone is getting into the game. Why? For a fraction of the cost, these APIs — what we at ProgrammableWeb sometimes call the PhD APIs — can do the same things that, just a few years ago, required a team of highly paid PhDs to accomplish.

But as impressive as all this dirt cheap rocket science is, we can’t help but laugh hysterically when it falls down. And that’s exactly what happened when one developer decided to publish a tutorial on how to use Microsoft’s Bing Speech Recognition API to transcribe a podcast using the C# language.

We’ll spare you the developers gory details on how to work with the API (although they’re quite good). However, it was not lost on us that the tutorial is in C# and the podcast that he attempted to transcribe was about Python. You can read the post to see the actual text that the API should have responded with. Meanwhile, here are the actual results (which remind us of some of Google Voice’s attempts to transcribe voice mails).

Are you considering getting into web programming cheese in the web Framework like plaster. Django can be daunting. It would be great to see them. Although that the same application and compare the results side by side. That’s Why? When I heard. But Nicholas Hunt. Walker was up to, I had him on the podcast. He night chat about 4 web frameworks, compared he built a data driven web app with last tornado. Peermade Angangueo and then put it all together in a presentation. We have dive into that right now. This is talk by the to me, I was 149 recorded January 30th 2018. Welcome to talk python to me a weekly podcast on Python Language the Library ecosystem in the personalities. Did you host Michael Kennedy? Follow me on Twitter where I’m at in Kennedy keep up with the show in the past episodes at talk python. Damn info, the show on Twitter via at Popeyes on. Nick Welcome to talk by phone.

Be sure to read the next Machine Learning article: What are the Best Python Tools for Machine Learning?

Original Article

Transcribing Podcasts with Microsoft Speech API