22.8 azspeech transcribe pipelines

20220314

We can pipe the output from transcribe to other tools. For example, we can analyse the sentiment of our spoken word by transcribing what we say from the computer’s microphone, and passing that text on to the sentiment command from the aztext MLHub package.

In the first example you might say happy days.

ml transcribe azspeech | ml sentiment aztext

The result is a most positive sentiment:

0.96

As another example you might say sad days.

ml transcribe azspeech | ml sentiment aztext

This time our utterance is identified as having quite a negative sentiment:

0.07

Pipelines can become quite powerful. Indeed, a pipeline can exhibit AI that might appear to be more than just the sum of its parts. Here, it transcribes the audio from the microphone, which for me would be English, translates it to French, cuts the actual text, and synthesizes it in a French voice.

ml transcribe azspeech |
  ml translate aztranslate --to=fr |
  cut -d',' -f4- |
  ml synthesize azspeech --voice=fr-FR-DeniseNeural

Voila



Your donation will support ongoing availability and give you access to the PDF version of this book. Desktop Survival Guides include Data Science, GNU/Linux, and MLHub. Books available on Amazon include Data Mining with Rattle and Essentials of Data Science. Popular open source software includes rattle, wajig, and mlhub. Hosted by Togaware, a pioneer of free and open source software since 1984. Copyright © 1995-2022 Graham.Williams@togaware.com Creative Commons Attribution-ShareAlike 4.0