Multiple Speakers 1

If your goal is to transcribe conversations, there will be more than one speaker. However, as you'll see, the recognize_google() function will only transcribe speech into a single block of text.

You can hear in this audio file there are three different speakers.

But if you transcribe it on its own, recognize_google() returns a single block of text. Which is still useful but it doesn't let you know which speaker said what.

We'll see an alternative to this in the next exercise.

The multiple speakers audio file has been imported and converted to AudioData as multiple_speakers.

This exercise is part of the course

Spoken Language Processing in Python

View Course

Exercise instructions

Create an instance of Recognizer.
Recognize the multiple_speakers variable using the recognize_google() function.
Set the language to US English ("en-US").

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Create a recognizer class
recognizer = sr.____()

# Recognize the multiple speaker AudioData
text = recognizer.recognize_google(____, 
                       			   language=____)

# Print the text
print(text)

Edit and Run Code