使用 MsAzure 服务密钥的语音转文本

Question

您好，我正在尝试使用 MsAzure Quick start GitHub Codes for Speech-to-text 将大型 (.wav) 音频文件转换为 .txt 文件。我已经粘贴了下面的代码。这些既不会产生结果，也不会产生任何错误消息。

def speech_recognize_continuous_from_file():
    """performs continuous speech recognition with input from an audio file"""
    # <SpeechContinuousRecognitionWithFile>
    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
    audio_config = speechsdk.audio.AudioConfig(filename=weatherfilename)

    speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)

    done = False

    def stop_cb(evt):
        """callback that stops continuous recognition upon receiving an event `evt`"""
        print('CLOSING on {}'.format(evt))
        speech_recognizer.stop_continuous_recognition()
        nonlocal done
        done = True

    all_results = []
    def handle_final_result(evt):
        all_results.append(evt.result.text)

    speech_recognizer.recognized.connect(handle_final_result)
    # 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)

    print("Printing all results:")
    print(all_results)

任何机构都可以建议我哪里出错了。 O最近几天挣扎了很多，没有任何有效的结果。 如果有人能建议我如何下载文本文件并将其保存在所需的文件夹中，我也很感激。

谢谢

Answer 1

如果您想将结果内容写入 .txt 文件，请尝试以下测试代码：

import azure.cognitiveservices.speech as speechsdk
import time

service_region = ''
speech_key=''
filename = 'D:/test.wav'
text_file_path = 'D:/temp/result.txt'

def speech_recognize_continuous_from_file():
    """performs continuous speech recognition with input from an audio file"""
    # <SpeechContinuousRecognitionWithFile>
    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
    audio_config = speechsdk.audio.AudioConfig(filename=filename)

    speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)

    done = False

    def stop_cb(evt):
        """callback that stops continuous recognition upon receiving an event `evt`"""
        print('CLOSING on {}'.format(evt))
        speech_recognizer.stop_continuous_recognition()
        nonlocal done
        done = True

    all_results = []
    def handle_final_result(evt):
        all_results.append(evt.result.text)

    speech_recognizer.recognized.connect(handle_final_result)
    # 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)

    print("writing result into txt file...")

    f = open(text_file_path, "w")
    for content in all_results:
        f.write(content)
    f.close()
    print("done.")

    print(all_results)
    

speech_recognize_continuous_from_file()

我将代码保存到单独的 .py 文件并直接运行，结果：