Google speech recognition API not listening

Question

I was trying the below speech recognition code using Google Speech API.

#!/usr/bin/env python3
# Requires PyAudio and PySpeech.

import speech_recognition as sr

# Record Audio
r = sr.Recognizer()
with sr.Microphone() as source:
    print("Say something!")
    audio = r.listen(source)

# Speech recognition using Google Speech Recognition
try:
    # for testing purposes, we're just using the default API key
    # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
    # instead of `r.recognize_google(audio)`
    print("You said: " + r.recognize_google(audio))
except sr.UnknownValueError:
    print("Google Speech Recognition could not understand audio")
except sr.RequestError as e:
    print("Could not request results from Google Speech Recognition service; {0}".format(e)) 

But I am getting only this.

jobin@jobin-Satellite-A665:~/scr$ python3 scr.py 
Say something!

Even though I say something, nothing happens.

I don't have an external microphone. I think this script will work with my laptop's in-built microphone.

I have tested my laptop's microphone here. It is working fine.

Am I missing anything?

Answer 1

You could test that pyAudio is finding your microphone by running the following:

"""PyAudio example: Record a few seconds of audio and save to a WAVE file."""

import pyaudio
import wave

CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 44100
RECORD_SECONDS = 5
WAVE_OUTPUT_FILENAME = "output.wav"

p = pyaudio.PyAudio()

stream = p.open(format=FORMAT,
                channels=CHANNELS,
                rate=RATE,
                input=True,
                frames_per_buffer=CHUNK)

print("* recording")

frames = []

for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
    data = stream.read(CHUNK)
    frames.append(data)

print("* done recording")

stream.stop_stream()
stream.close()
p.terminate()

wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()

And playing the resulting output.wav file.

Once you are confident that you are getting some audio I would add a couple of print statements to the original code to locate how far you are getting, i.e.:

print("Audio captured!") # before trying to recognise see if you have something

and

print('Recognition Ended')  # at the end of the script

This will let you see how far you are getting.

Next you may need to find out which is the default audio device with:

import pyaudio
print(pyaudio.pa.get_default_input_device())

Which should tell you the default input device, this was one on my machine so used this:

with sr.Microphone(1) as source: # Specify which input device to use
    r.adjust_for_ambient_noise(source, 1) # Adjust for ambient
    print("Say something!")
    audio = r.listen(source, 2)  # 2 Second time out
print('Done Listening sample size =', len(audio.frame_data))