如何使用Google Cloud API和Python触发流式语音识别

首先，我对python和这个网站都很陌生，所以请耐心听我说

我已经使用googlecloud站点（）提供的示例代码成功地从现场麦克风输入执行了语音识别，我希望在另一个python脚本触发该过程时启动和停止该过程。为此，我尝试在程序到达使其循环的程序末尾的“main（）”调用行之前使用While循环停止程序，并将其保持在那里，直到某个变量发生更改。这会在我需要时成功启动语音识别，但也会产生各种错误和问题（输出总是不同的，有时程序只是在没有通知的情况下退出，其他时候它会说没有输入设备或无法连接到服务器）

在我需要的时候运行整个python程序也不是一个选项，因为这需要一些时间，我负担不起延迟。我在互联网上搜索了一个解决方案，但没有找到。如果有人能给我一个如何完成我正在寻找的方向，我会非常感激

以下是示例代码：

from __future__ import division

import re
import sys

from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
import pyaudio
from six.moves import queue

# Audio recording parameters
RATE = 16000
CHUNK = int(RATE / 10)  # 100ms


class MicrophoneStream(object):
    """Opens a recording stream as a generator yielding the audio chunks."""
    def __init__(self, rate, chunk):
        self._rate = rate
        self._chunk = chunk

        # Create a thread-safe buffer of audio data
        self._buff = queue.Queue()
        self.closed = True

    def __enter__(self):
        self._audio_interface = pyaudio.PyAudio()
        self._audio_stream = self._audio_interface.open(
            format=pyaudio.paInt16,
            # The API currently only supports 1-channel (mono) audio
            channels=1, rate=self._rate,
            input=True, frames_per_buffer=self._chunk,
            # Run the audio stream asynchronously to fill the buffer object.
            # This is necessary so that the input device's buffer doesn't
            # overflow while the calling thread makes network requests, etc.
            stream_callback=self._fill_buffer,
        )

        self.closed = False

        return self

    def __exit__(self, type, value, traceback):
        self._audio_stream.stop_stream()
        self._audio_stream.close()
        self.closed = True
        # Signal the generator to terminate so that the client's
        # streaming_recognize method will not block the process termination.
        self._buff.put(None)
        self._audio_interface.terminate()

    def _fill_buffer(self, in_data, frame_count, time_info, status_flags):
        """Continuously collect data from the audio stream, into the buffer."""
        self._buff.put(in_data)
        return None, pyaudio.paContinue

    def generator(self):
        while not self.closed:
            # Use a blocking get() to ensure there's at least one chunk of
            # data, and stop iteration if the chunk is None, indicating the
            # end of the audio stream.
            chunk = self._buff.get()
            if chunk is None:
                return
            data = [chunk]

            # Now consume whatever other data's still buffered.
            while True:
                try:
                    chunk = self._buff.get(block=False)
                    if chunk is None:
                        return
                    data.append(chunk)
                except queue.Empty:
                    break

            yield b''.join(data)


def listen_print_loop(responses):
    """Iterates through server responses and prints them.

    The responses passed is a generator that will block until a response
    is provided by the server.

    Each response may contain multiple results, and each result may contain
    multiple alternatives.  Here we
    print only the transcription for the top alternative of the top result.

    In this case, responses are provided for interim results as well. If the
    response is an interim one, print a line feed at the end of it, to allow
    the next result to overwrite it, until the response is a final one. For the
    final one, print a newline to preserve the finalized transcription.
    """
    num_chars_printed = 0
    for response in responses:
        if not response.results:
            continue

        # The `results` list is consecutive. For streaming, we only care about
        # the first result being considered, since once it's `is_final`, it
        # moves on to considering the next utterance.
        result = response.results[0]
        if not result.alternatives:
            continue

        # Display the transcription of the top alternative.
        transcript = result.alternatives[0].transcript

        # Display interim results, but with a carriage return at the end of the
        # line, so subsequent lines will overwrite them.
        #
        # If the previous result was longer than this one, we need to print
        # some extra spaces to overwrite the previous result
        overwrite_chars = ' ' * (num_chars_printed - len(transcript))

        if not result.is_final:
            sys.stdout.write(transcript + overwrite_chars + '\r')
            sys.stdout.flush()

            num_chars_printed = len(transcript)

        else:
            print(transcript + overwrite_chars)

            # Exit recognition if any of the transcribed phrases could be
            # one of our keywords.
            if re.search(r'\b(exit|quit)\b', transcript, re.I):
                print('Exiting..')
                break

            num_chars_printed = 0


def main():
    # See http://g.co/cloud/speech/docs/languages
    # for a list of supported languages.
    language_code = 'en-US'  # a BCP-47 language tag

    client = speech.SpeechClient()
    config = types.RecognitionConfig(
        encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=RATE,
        language_code=language_code)
    streaming_config = types.StreamingRecognitionConfig(
        config=config,
        interim_results=True)

    with MicrophoneStream(RATE, CHUNK) as stream:
        audio_generator = stream.generator()
        requests = (types.StreamingRecognizeRequest(audio_content=content)
                    for content in audio_generator)

        responses = client.streaming_recognize(streaming_config, requests)

        # Now, put the transcription responses to use.
        listen_print_loop(responses)


if __name__ == '__main__':
    main()