azure - Azure 语音转文本教程

Question

我想使用 Azure Speech to Text 将音频文件转换为文本数据。有人知道这方面的好教程吗？我可以在下面找到一个教程: https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/quickstart-python

但是示例的音频源来自麦克风而不是音频文件。

谢谢。

Answer 1

有一个名为 whatstheweatherlike.wav 的官方音频样本您可以从 samples/csharp/sharedcontent/console/whatstheweatherlike.wav 获取GitHub 存储库 Azure-Samples/cognitive-services-speech-sdk。

这是我编写的示例代码，部分引用了官方教程 Quickstart: Recognize speech with the Speech SDK for Python 。我通过 pip install azure-cognitiveservices-speech 安装了当前版本的 Azure 语音认知服务 SDK 1.6.0。

import azure.cognitiveservices.speech as speechsdk

speech_key, service_region = "<your api key>", "<your region>"
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)

audio_config = speechsdk.audio.AudioConfig(filename='whatstheweatherlike.wav')
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
result = speech_recognizer.recognize_once()
print(result.text)

从音频样本文件中识别出的文本如下。

What's the weather like?

希望有帮助。