连续从子进程中获取变量数据

Question

我有一个子进程不断监听麦克风，将音频转换为文本并存储结果。代码是

from os import environ, path
import pyaudio
from utils import micStream
from pocketsphinx.pocketsphinx import *
from sphinxbase.sphinxbase import *

MODELDIR = "PATH TO MODEL"

config = Decoder.default_config()
config.set_string('-hmm', path.join(MODELDIR, 'en-us/acoustic-model'))
config.set_string('-lm', path.join(MODELDIR, 'en-us/language-model.lm.bin'))
config.set_string('-dict', path.join(MODELDIR, 'en-us/language-dictionary.dict'))
config.set_string('-logfn', 'nul')
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(decoder.hyp().hypstr.lower())

                decoder.start_utt()
    else:
        break
decoder.end_utt()

我正在尝试运行这作为一个子进程，并让父进程连续读取字符串 decoder.hyp().hypstr.lower() 而不会阻塞主进程的其余部分。我试过了

subprocess.check_output() 和 listener=subprocess.Popen([sys.executable,'file_name'])

但两者似乎都阻止了我的代码。有办法吗？

Answer 1

您可以尝试这样的操作：


from multiprocessing import Process, Queue          # ADD IMPORT

from os import environ, path
import pyaudio
from utils import micStream
from pocketsphinx.pocketsphinx import *
from sphinxbase.sphinxbase import *


def get_audio(q):
    MODELDIR = "PATH TO MODEL"

    config = Decoder.default_config()
    config.set_string('-hmm', path.join(MODELDIR, 'en-us/acoustic-model'))
    config.set_string('-lm', path.join(MODELDIR, 'en-us/language-model.lm.bin'))
    config.set_string('-dict', path.join(MODELDIR, 'en-us/language-dictionary.dict'))
    config.set_string('-logfn', 'nul')
    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()
                    q.put(decoder.hyp().hypstr.lower())    # PUT THE OUTPUT INTO QUEUE
                    decoder.start_utt()
        else:
            break
    decoder.end_utt()

out_q = Queue()
audio_p = Process(target=get_audio, args=(out_q,))
audio_p.start()

while True:
    # If data has been received process it
    if not out_q.empty():
        res = out_q.get()
        # Perform whatever needs to happen when the parent receives the output here
    # After processing the data, or if no data has been received
    # Put the code that needs to run in the main process here

连续从子进程中获取变量数据

Get variable data from subprocess continuously

python

subprocess

speech-to-text