def setup(self):
# PocketSphinx configuration
ps_config = Decoder.default_config()
# Set recognition model to US
ps_config.set_string('-hmm', os.path.join(get_model_path(), 'en-us'))
ps_config.set_string('-dict', os.path.join(get_model_path(), 'cmudict-en-us.dict'))
# Specify recognition key phrase
ps_config.set_string('-keyphrase', self._tconfig['phrase'])
ps_config.set_float('-kws_threshold', float(self._tconfig['threshold']))
# Hide the VERY verbose logging information when not in debug
if logging.getLogger('alexapi').getEffectiveLevel() != logging.DEBUG:
ps_config.set_string('-logfn', '/dev/null')
# Process audio chunk by chunk. On keyword detected perform action and restart search
self._decoder = Decoder(ps_config)
"""
https://pypi.org/project/pocketsphinx/
https://cmusphinx.github.io/wiki/
"""
import os
from pocketsphinx import LiveSpeech, get_model_path
model_path = get_model_path()
speech = LiveSpeech(
verbose=False,
sampling_rate=16000,
buffer_size=2048,
no_search=False,
full_utt=False,
hmm=os.path.join(model_path, 'en-us'),
lm=os.path.join(model_path, 'en-us.lm.bin'),
dic=os.path.join(model_path, 'cmudict-en-us.dict')
)
for phrase in speech:
print(phrase)
from alexapi.device_platforms.desktop import DesktopPlatform
platform = DesktopPlatform(config)
# Setup
recorded = False
servers = ["127.0.0.1:11211"]
mc = Client(servers, debug=1)
path = os.path.realpath(__file__).rstrip(os.path.basename(__file__))
resources_path = os.path.join(path, 'resources', '')
tmp_path = os.path.join(tempfile.mkdtemp(prefix='AlexaPi-runtime-'), '')
# PocketSphinx configuration
ps_config = Decoder.default_config()
# Set recognition model to US
ps_config.set_string('-hmm', os.path.join(get_model_path(), 'en-us'))
ps_config.set_string('-dict', os.path.join(get_model_path(), 'cmudict-en-us.dict'))
# Specify recognition key phrase
ps_config.set_string('-keyphrase', config['sphinx']['trigger_phrase'])
ps_config.set_float('-kws_threshold', 1e-5)
# Hide the VERY verbose logging information
if not debug:
ps_config.set_string('-logfn', '/dev/null')
# Process audio chunk by chunk. On keyword detected perform action and restart search
decoder = Decoder(ps_config)
decoder.start_utt()
# Variables
import os
from pocketsphinx import LiveSpeech, get_model_path
model_path = get_model_path()
BASE_PATH = os.path.dirname(os.path.realpath(__file__))
HMDIR = os.path.join(BASE_PATH, "hmm/en-us/cmusphinx-en-us.tar.gz")
LMDIR = os.path.join(BASE_PATH, "lm/en-us/en-us.lm.bin")
DICTD = os.path.join(BASE_PATH, "dict/en-us/cmudict-en-us.dict")
print(LMDIR)
print(os.path.join(model_path, 'en-us/en-us.lm.bin'))
speech = LiveSpeech(
verbose=False,
sampling_rate=16000,
buffer_size=2048,
no_search=False,
full_utt=False,
hmm=os.path.join(model_path, 'en-us'),
lm=os.path.join(model_path, 'en-us.lm.bin'),
dic=os.path.join(model_path, 'cmudict-en-us.dict')
)
for phrase in speech:
print(phrase)
platform = DesktopPlatform(config)
#Setup
recorded = False
servers = ["127.0.0.1:11211"]
mc = Client(servers, debug=1)
path = os.path.realpath(__file__).rstrip(os.path.basename(__file__))
resources_path = os.path.join(path, 'resources', '')
tmp_path = os.path.join(tempfile.mkdtemp(prefix='AlexaPi-runtime-'), '')
# PocketSphinx configuration
ps_config = Decoder.default_config()
# Set recognition model to US
ps_config.set_string('-hmm', os.path.join(get_model_path(), 'en-us'))
ps_config.set_string('-dict', os.path.join(get_model_path(), 'cmudict-en-us.dict'))
#Specify recognition key phrase
ps_config.set_string('-keyphrase', config['sphinx']['trigger_phrase'])
ps_config.set_float('-kws_threshold',1e-5)
# Hide the VERY verbose logging information
ps_config.set_string('-logfn', '/dev/null')
# Process audio chunk by chunk. On keyword detected perform action and restart search
decoder = Decoder(ps_config)
decoder.start_utt()
#Variables
p = None
""" Constants, used by the app
Attributes:
_PACKAGE_LOCATION (str): location of the application
WORKING_DIRECTORY (str): location of the working directory within the application
SPEECH_MODEL_PATH (str): location of the speech recognition model
SPEECH_DATA_PATH (str): location of the speech recognition data, used by the pocketsphinx library
"""
import os
from pocketsphinx import get_data_path, get_model_path
_PACKAGE_LOCATION = '/'.join(os.path.realpath(__file__).split('/')[:-2])
WORKING_DIRECTORY = _PACKAGE_LOCATION
SPEECH_MODEL_PATH = get_model_path()
SPEECH_DATA_PATH = get_data_path()
if __name__ == '__main__':
print(WORKING_DIRECTORY)
Всегда работают 2 процесса:
'''
import wave
import time
import math
import struct
import threading
import os
from os import path
import numpy as np
import pyaudio
from pocketsphinx import get_model_path
from pocketsphinx.pocketsphinx import *
modeldir = get_model_path() # директория, где лежат файлы словаря PocketSphinx
md = path.dirname(__file__)
# Create a decoder with certain model
config = Decoder.default_config()
config.set_string('-logfn', '/dev/null')
config.set_string('-hmm', os.path.join(modeldir, 'en-us'))
config.set_string('-dict', os.path.join(md, '8070.dic'))
config.set_string('-lm', os.path.join(md, '8070.lm'))
THRESHOLD = 15 # Порог громкости, если звук выше - сработает распознавание
PRE_REC_LEN = 3 # длина предзаписи(чтоб ловить начало слова)
REC_LEN = 8 # длина записи самого слова
SHORT_NORMALIZE = (1.0 / 32768.0)
CHUNK = 6144 # длина массива для записи 1 кванта звука для 48КГц
RATE = 16000
THRESHOLD = 1000 # The threshold intensity that defines silence
# and noise signal (an int. lower than THRESHOLD is silence).
SILENCE_LIMIT = 1 # Silence limit in seconds. The max ammount of seconds where
# only silence is recorded. When this time passes the
# recording finishes and the file is delivered.
PREV_AUDIO = 1.0 # Previous audio (in seconds) to prepend. When noise
# is detected, how much of previously recorded audio is
# prepended. This helps to prevent chopping the beggining
# of the phrase.
HOTWORD_THRESHOLD = -5000 # Higher values indicate that pocketsphinx
# is sure about the word. Adjust to your needs.
# Pocketsphinx files
MODELDIR = get_model_path() # Default model path, replace if
# you use a custom model in a custom location.
# WORDS
HOTWORD = "Anastasia"
SPEAK_UNDERSTOOD = "Understood."
SPEAK_FAILURE = "Sorry?"
SPEAK_SUCCESS = "Okay."
SPEAK_READY = HOTWORD + ". At your service."
# Decoder setup
config = DefaultConfig()
config.set_string('-hmm', path.join(MODELDIR, 'en-us'))
# you can use a custom model
config.set_string('-lm', path.join(MODELDIR, 'en-us.lm.bin'))
# you can use a custom dictionary
try:
import google.cloud.speech
import google.auth.exceptions
except (ImportError, ModuleNotFoundError):
logging.warning(
"Speech-to-text recognition using Google online services is not "
"available (use command `pip install google-api-core google-auth "
"google-cloud google-cloud-speech googleapis-common-protos` to get "
"it). Transcription will be unavailable using that service this "
"session.")
_hasGoogleCloud = False
try:
import pocketsphinx
sphinxLangs = [folder.stem for folder
in Path(pocketsphinx.get_model_path()).glob('??-??')]
haveSphinx = True
except ModuleNotFoundError:
haveSphinx = False
sphinxLangs = None
# Constants related to the transcription system.
TRANSCR_LANG_DEFAULT = 'en-US'
# Values for specifying recognizer engines. This dictionary is used by Builder
# to populate the component property dropdown.
recognizerEngineValues = {
0: ('sphinx', "CMU Pocket Sphinx", "Offline, Built-in"),
1: ('google', "Google Cloud Speech API", "Online, Key Required"),
}
