Pocketsphinx

Pocketsphinx est une librairie permettant d'intégrer la reconnaissance vocale dans vos projets écrit en language C à l'aide des fonctionnalités du projet open source CMUSphinx.

Installer les paquets python-pocketsphinx libpocketsphinx1 gstreamer0.10-pocketsphinx python-pyaudio.

Ou dans un terminal avec les droits administrateurs :

sudo apt-get install python-pocketsphinx libpocketsphinx1 gstreamer0.10-pocketsphinx python-pyaudio

D'abord il faut installer les dépendances dans un terminal avec les droits administrateurs :

sudo apt-get build-dep pocketsphinx
sudo apt-get install bison python-pyaudio

On récupère ensuite les sources de sphinxbase-0.8

wget -O sphinxbase-0.8.tar.gz http://sourceforge.net/projects/cmusphinx/files/sphinxbase/0.8/sphinxbase-0.8.tar.gz/download

On les décompresse

tar -xvzf sphinxbase-0.8.tar.gz

On compile

./configure --prefix=/usr/local
make
sudo make install

    import pocketsphinx as ps
  File "sphinxbase.pxd", line 150, in init pocketsphinx (pocketsphinx.c:7935)
ValueError: PyCapsule_GetPointer called with invalid PyCapsule object

sudo apt-get install cython
mv python/sphinxbase.c ~

sudo apt-get remove libpulse-dev

wget -O pocketsphinx-0.8.tar.gz http://sourceforge.net/projects/cmusphinx/files/pocketsphinx/0.8/pocketsphinx-0.8.tar.gz/download
tar -xvzf pocketsphinx-0.8.tar.gz
cd pocketsphinx-0.8
./configure --prefix=/usr/local
make
sudo make install

Téléchargement:

wget -O lium_french_f0.tar.gz http://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/French%20F0%20Broadcast%20News%20Acoustic%20Model/lium_french_f0.tar.gz/download
tar -xvzf lium_french_f0.tar.gz
cd lium_french_f0/
sudo mkdir -p `pkg-config --variable=modeldir pocketsphinx`/hmm/fr_FR/french_f0
sudo mv * `pkg-config --variable=modeldir pocketsphinx`/hmm/fr_FR/french_f0

wget -O french3g62K.lm.dmp.bz2 http://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/French%20Language%20Model/french3g62K.lm.dmp.bz2/download
bzip2 -d french3g62K.lm.dmp.bz2
sudo mkdir -p `pkg-config --variable=modeldir pocketsphinx`/lm/fr_FR/
sudo mv french3g62K.lm.dmp `pkg-config --variable=modeldir pocketsphinx`/lm/fr_FR/

wget -O frenchWords62K.dic http://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/French%20Language%20Model/frenchWords62K.dic/download
sudo mv frenchWords62K.dic `pkg-config --variable=modeldir pocketsphinx`/lm/fr_FR/


wget -O lium_french_f2.tar.gz http://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/French%20F2%20Telephone%20Acoustic%20Model/lium_french_f2.tar.gz/download

pocketsphinx_continuous -dict /usr/share/pocketsphinx/model/FR/frenchWords62K.dic -hmm /usr/share/pocketsphinx/model/FR/ -lm /usr/share/pocketsphinx/model/FR/french3g62K.lm.dmp

ref

#!/usr/bin/python
"""
PyAudio Example:
 
Query and print PortAudio HostAPIs, Devices, and their
support rates.
"""
 
import pyaudio
 
standard_sample_rates = [8000.0, 9600.0, 11025.0, 12000.0,
                         16000.0, 22050.0, 24000.0, 32000.0,
                         44100.0, 48000.0, 88200.0, 96000.0,
                         192000.0]
 
p = pyaudio.PyAudio()
max_apis = p.get_host_api_count()
max_devs = p.get_device_count()
 
print("\nPortAudio System Info:\n======================")
print("Version: %d" % pyaudio.get_portaudio_version())
print("Version Text: %s" % pyaudio.get_portaudio_version_text())
print("Number of Host APIs: %d" % max_apis)
print("Number of Devices  : %d" % max_devs)
 
print("\nHost APIs:\n==========")
 
for i in range(max_apis):
    apiinfo = p.get_host_api_info_by_index(i)
    for k in list(apiinfo.items()):
        print("%s: %s" % k)
    print("--------------------------")
 
print("\nDevices:\n========")
 
for i in range(max_devs):
    devinfo = p.get_device_info_by_index(i)
 
    # print out device parameters
    for k in list(devinfo.items()):
        name, value = k
 
        # if host API, then get friendly name
 
        if name == 'hostApi':
            value = str(value) + \
                    " (%s)" % p.get_host_api_info_by_index(k[1])['name']
        print("\t%s: %s" % (name, value))
 
    # print out supported format rates
 
    input_supported_rates = []
    output_supported_rates = []
    full_duplex_rates = []
 
    for f in standard_sample_rates:
 
        if devinfo['maxInputChannels'] > 0:
            try:
                if p.is_format_supported(
                    f,
                    input_device = devinfo['index'],
                    input_channels = devinfo['maxInputChannels'],
                    input_format = pyaudio.paInt16):
                    input_supported_rates.append(f)
            except ValueError:
                pass
 
        if devinfo['maxOutputChannels'] > 0:
            try:
                if p.is_format_supported(
                    f,
                    output_device = devinfo['index'],
                    output_channels = devinfo['maxOutputChannels'],
                    output_format = pyaudio.paInt16):
                    output_supported_rates.append(f)
            except ValueError:
                pass
 
        if (devinfo['maxInputChannels'] > 0) and \
           (devinfo['maxOutputChannels'] > 0):
            try:
                if p.is_format_supported(
                    f,
                    input_device = devinfo['index'],
                    input_channels = devinfo['maxInputChannels'],
                    input_format = pyaudio.paInt16,
                    output_device = devinfo['index'],
                    output_channels = devinfo['maxOutputChannels'],
                    output_format = pyaudio.paInt16):
                    full_duplex_rates.append(f)
            except ValueError:
                pass
 
    if len(input_supported_rates):
        print("\tInput rates: %s" % input_supported_rates)
    if len(output_supported_rates):
        print("\tOutput rates: %s" % output_supported_rates)
    if len(full_duplex_rates):
        print("\tFull duplex: %s" % full_duplex_rates)
 
    print("\t--------------------------------")
 
print("\nDefault Devices:\n================")
try:
    def_index = p.get_default_input_device_info()['index']
    print("Default Input Device : %s" % def_index)
    devinfo = p.get_device_info_by_index(def_index)
    for k in list(devinfo.items()):
        name, value = k
        if name == 'hostApi':
            value = str(value) + \
                    " (%s)" % p.get_host_api_info_by_index(k[1])['name']
        print("\t%s: %s" % (name, value))
    print("\t--------------------------------")
except IOError as e:
    print("No Input devices: %s" % e[0])
 
try:
    def_index = p.get_default_output_device_info()['index']
    print("Default Output Device: %s" % def_index)
    devinfo = p.get_device_info_by_index(def_index)
    for k in list(devinfo.items()):
        name, value = k
        if name == 'hostApi':
            value = str(value) + \
                    " (%s)" % p.get_host_api_info_by_index(k[1])['name']
        print("\t%s: %s" % (name, value))
    print("\t--------------------------------")
except IOError as e:
    print("No Output devices: %s" % e[0])
 
p.terminate()

ref

#!/usr/bin/python
 
import sys,os
import pyaudio
import wave
 
hmdir = "/usr/share/pocketsphinx/model/FR/"
lmd = "/usr/share/pocketsphinx/model/FR/french3g62K.lm.dmp"
dictd = "/usr/share/pocketsphinx/model/FR/frenchWords62K.dic"
 
def decodeSpeech(hmmd,lmdir,dictp,wavfile):
 
    import pocketsphinx as ps
    import sphinxbase
 
    speechRec = ps.Decoder(hmm = hmmd, lm = lmdir, dict = dictp)
    wavFile = file(wavfile,'rb')
    wavFile.seek(44)
    speechRec.decode_raw(wavFile)
    result = speechRec.get_hyp()
 
    return result[0]
 
#CHUNK = 1024
CHUNK = 512
#FORMAT = pyaudio.paInt16
FORMAT = pyaudio.paALSA
CHANNELS = 1
RATE = 16000
#RATE = 44100
RECORD_SECONDS = 10
 
for x in range(10):
    fn = "o"+str(x)+".wav"
    p = pyaudio.PyAudio()
    stream = p.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK)
    print("* recording")
    frames = []
    print str(RATE / CHUNK * RECORD_SECONDS) + " size\n"
    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()
    wf = wave.open(fn, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    p.terminate()
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()
    wavfile = fn
    recognised = decodeSpeech(hmdir,lmd,dictd,wavfile)
    print recognised
    cm = 'espeak "'+recognised+'"'
    os.system(cm)

• Site officiel : http://cmusphinx.sourceforge.net/wiki/download/
• Python audio : http://people.csail.mit.edu/hubert/pyaudio/docs/
• Exemple en python: http://pythonism.wordpress.com/2013/06/06/pocketsphinx-voice-recognition-with-python/
• http://stackoverflow.com/questions/8567366/geting-ioerror-errno-input-overflowed-9981-when-setting-pyaudio-stream-input
• installer sur raspberry pi :http://stackoverflow.com/questions/17778532/raspberrypi-pocketsphinx-ps3eye-error-failed-to-open-audio-device