548 reads

Speech Recognition using Python

by Gaurav KumarMay 8th, 2020

Too Long; Didn't Read

SpeechRecognition is based on a version version 3.8.1. Each Recognizer instance has seven methods for recognizing speech from an audio source using various APIs. Only recognize_sphinx() works offline with the CMU Sphinx engine. The other six all require an internet connection to recognize speech using the API. Each recognize_*() method will throw a speech_recognition.RequestError exception if the API is unreachable. The other 6 methods require a connection to the server.

Companies Mentioned

featured image - Speech Recognition using Python

Install SpeechRecognition

$ pip install SpeechRecognitionAfter Installation, verify the version

>>> import speech_recognition as sr

>>> sr.__version__

'3.8.1'

Recognizer Class in SpeechRecognition

Key Implementations done by SpeechRecognition using the Recognizer class. Primary purpose of Recognizer instance is to recognize speech. Each instance comes with a variety of settings and functionality for recognizing speech from an audio source. Creating a Recognizer instance is easy. In your current interpreter session, just type:

>>> r = sr.Recognizer()

Methods for Recognizing Speech

Each Recognizer instance has seven methods for recognizing speech from an audio source using various APIs

recognize_bing(): Microsoft Bing Speech
recognize_google(): Google Web Speech API
recognize_google_cloud(): Google Cloud Speech - requires installation of the google-cloud-speech package
recognize_houndify(): Houndify by SoundHound
recognize_ibm(): IBM Speech to Text
recognize_sphinx(): CMU Sphinx - requires installing PocketSphinx
recognize_wit(): Wit.ai

Of the seven, only recognize_sphinx() works offline with the CMU Sphinx engine. The other six all require an internet connection.

Recognizing Speech

Each recognize_*() method will throw a speech_recognition.RequestError exception if the API is unreachable. For recognize_sphinx(), this could happen as the result of a missing, corrupt or incompatible Sphinx installation. For the other six methods, RequestError may be thrown if quota limits are met, the server is unavailable, or there is no internet connection.

Call recognize_google()

>>> r.recognize_google()

Adding Audio Files for Speech Recognition

Now, record the WAV File so that it can be translated to text. Any WAV file can be taken

Speech Extraction Google API

import speech_recognition as sr

harvard=sr.AudioFile('myrecord.wav')

r = sr.Recognizer()

with harvard as source:
    audio=r.record(source)

print (type(audio))

print (r.recognize_google(audio))

The text will be recognized from audio file "myaudio.wav" and will be printed

L O A D I N G
. . . comments & more!