问Azure认知服务/语音到文本:转录压缩PCMU (mu-law) wav文件

EN

import azure.cognitiveservices.speech as speechsdk

def azurespeech_transcribe(audio_filename):
    class BinaryFileReaderCallback(speechsdk.audio.PullAudioInputStreamCallback):
        def __init__(self, filename: str):
            super().__init__()
            self._file_h = open(filename, "rb")

        def read(self, buffer: memoryview) -> int:
            try:
                size = buffer.nbytes
                frames = self._file_h.read(size)
                buffer[:len(frames)] = frames
                return len(frames)
            except Exception as ex:
                print('Exception in `read`: {}'.format(ex))
                raise

        def close(self) -> None:
            try:
                self._file_h.close()
            except Exception as ex:
                print('Exception in `close`: {}'.format(ex))
                raise
    compressed_format = speechsdk.audio.AudioStreamFormat(
        compressed_stream_format=speechsdk.AudioStreamContainerFormat.MULAW
    )
    callback = BinaryFileReaderCallback(filename=audio_filename)
    stream = speechsdk.audio.PullAudioInputStream(
        stream_format=compressed_format,
        pull_stream_callback=callback
    )
    speech_config = speechsdk.SpeechConfig(
        subscription="<my_subscription_key>",
        region="<my_region>",
        speech_recognition_language="en-CA"
    )
    audio_config = speechsdk.audio.AudioConfig(stream=stream)
    speech_recognizer = speechsdk.SpeechRecognizer(speech_config, audio_config)
    result = speech_recognizer.recognize_once()
    return result.text