我正在尝试将数据发送到 azure Speech SDK 进行转录。我希望它从 python 文件接收数据，放入缓冲区，然后连续转录。我正在使用来自 azure Speech SDK 的这个示例。
def speech_recognition_with_pull_stream():
"""gives an example how to use a pull audio stream to recognize speech from a custom audio
source"""
class WavFileReaderCallback(speechsdk.audio.PullAudioInputStreamCallback):
"""Example class that implements the Pull Audio Stream interface to recognize speech from
an audio file"""
def __init__(self, filename: str):
super().__init__()
self._file_h = wave.open(filename, mode=None)
self.sample_width = self._file_h.getsampwidth()
assert self._file_h.getnchannels() == 1
assert self._file_h.getsampwidth() == 2
assert self._file_h.getframerate() == 16000
assert self._file_h.getcomptype() == 'NONE'
def read(self, buffer: memoryview) -> int:
"""read callback function"""
size = buffer.nbytes
frames = self._file_h.readframes(size // self.sample_width)
buffer[:len(frames)] = frames
return len(frames)
def close(self):
"""close callback function"""
self._file_h.close()
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
# specify the audio format
wave_format = speechsdk.audio.AudioStreamFormat(samples_per_second=16000, bits_per_sample=16,
channels=1)
# setup the audio stream
callback = WavFileReaderCallback(weatherfilename)
stream = speechsdk.audio.PullAudioInputStream(callback, wave_format)
audio_config = speechsdk.audio.AudioConfig(stream=stream)
# instantiate the speech recognizer with pull stream input
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
done = False
def stop_cb(evt):
"""callback that signals to stop continuous recognition upon receiving an event `evt`"""
print('CLOSING on {}'.format(evt))
nonlocal done
done = True
# Connect callbacks to the events fired by the speech recognizer
speech_recognizer.recognizing.connect(lambda evt: print('RECOGNIZING: {}'.format(evt)))
speech_recognizer.recognized.connect(lambda evt: print('RECOGNIZED: {}'.format(evt)))
speech_recognizer.session_started.connect(lambda evt: print('SESSION STARTED: {}'.format(evt)))
speech_recognizer.session_stopped.connect(lambda evt: print('SESSION STOPPED {}'.format(evt)))
speech_recognizer.canceled.connect(lambda evt: print('CANCELED {}'.format(evt)))
# stop continuous recognition on either session stopped or canceled events
speech_recognizer.session_stopped.connect(stop_cb)
speech_recognizer.canceled.connect(stop_cb)
# Start continuous speech recognition
speech_recognizer.start_continuous_recognition()
while not done:
time.sleep(.5)
speech_recognizer.stop_continuous_recognition()
我不想从音频文件'callback = WavFileReaderCallback(weatherfilename)'中获取数据，而是想从另一个通过以下方式发送数据的python文件中获取数据：
tcp_client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
.
.
.
tcp_client.sendall(bytes(data))
如何将这些数据放入语音 SDK 转录的缓冲区。请指导，谢谢。