Python pocketsphinx recognition from the microphone

Question

I have installed and setup both pocketsphinx and sphinxbase packages in python. I have also taken code of speech recognition for github and changed both data and mode directory as per requirement but still it is unable to stream by voice when I am trying to run it by "python test.py" Here is the code:

#!/usr/bin/env python
import os
import sphinxbase as sb
import pocketsphinx as ps

MODELDIR = '/usr/lib/python2.7/site-packages/speech_recognition/pocketsphinx-data'
DATADIR='/usr/lib/python2.7/site-packages/speech_recognition/pocketsphinx-data'
# Create a decoder with certain model
config = ps.Decoder.default_config()
config.set_string('-hmm', "/usr/lib/python2.7/site-packages/speech_recognition/pocketsphinx-data/en-US/acoustic-model")
config.set_string('-lm', os.path.join(MODELDIR, 'en-US/language-model.lm.bin'))
config.set_string('-dict', os.path.join(MODELDIR, 'en-US/pronounciation-dictionary.dict'))
decoder = ps.Decoder(config)

# Decode streaming data.
decoder.start_utt()
stream = open(os.path.join(DATADIR, 'en-US/goforward.raw'), 'rb')
while True: 
    buf = stream.read(1024)
    if buf:
        decoder.process_raw(buf, False, False)
    else:
        break
decoder.end_utt()
stream.close()
print('Best hypothesis segments:', [seg.word for seg in decoder.seg()])

Please tell me how to execute it.

Actually, there is no exact problem on the terminal. It is printing all the details of the modules correctly but it is not streaming(taking any vice input) when I am trying to execute it. — Krishna Agarwal, Aug 08 '16 at 14:02
For recording microphone you need to take pyaudio stream, you can find samples in sources — Nikolay Shmyrev, Aug 10 '16 at 15:33

score 8 · Accepted Answer · answered Aug 10 '16 at 15:36

Continuous recognition from microphone should look like this:

#!/usr/bin/python

from os import environ, path
import pyaudio

from pocketsphinx.pocketsphinx import *
from sphinxbase.sphinxbase import *

MODELDIR = "../../../model"

config = Decoder.default_config()
config.set_string('-hmm', path.join(MODELDIR, 'en-us/en-us'))
config.set_string('-lm', path.join(MODELDIR, 'en-us/en-us.lm.bin'))
config.set_string('-dict', path.join(MODELDIR, 'en-us/cmudict-en-us.dict'))
decoder = Decoder(config)

p = pyaudio.PyAudio()
stream = p.open(format=pyaudio.paInt16, channels=1, rate=16000, input=True, frames_per_buffer=1024)
stream.start_stream() 

in_speech_bf = False
decoder.start_utt()
while True:
    buf = stream.read(1024)
    if buf:
        decoder.process_raw(buf, False, False)
        if decoder.get_in_speech() != in_speech_bf:
            in_speech_bf = decoder.get_in_speech()
            if not in_speech_bf:
                decoder.end_utt()
                print 'Result:', decoder.hyp().hypstr
                decoder.start_utt()
    else:
        break
decoder.end_utt()

When I run your code, I have this Error: `error: command 'swig.exe' failed: No such file or directory` `ERROR: Failed building wheel for pocketsphinx` — mehdi alizade, Sep 25 '21 at 19:22
@mehdializade `swig` is a command required to build `pocketsphinx`. You should be able to install swig on Windows using the information in [this question](https://stackoverflow.com/q/7443112/16775594). — Sylvester Kruin, Dec 28 '21 at 14:24
This code gives me large error messages when I run it; is there a Python 3 equivalent? — Sylvester Kruin, Dec 28 '21 at 14:51
@SylvesterKruin wrap the print command in brackets. `print ('Result:', decoder.hyp().hypstr)` — twobob, Jun 13 '22 at 02:24

Python pocketsphinx recognition from the microphone

1 Answers1

Linked