如何使用Azure语音批量转录文本-Python代码

Question

我在使用Azure语音到Python中的文本Api REST连接天蓝色斑点时遇到问题。如果有人在Python中提供了示例代码，如果您能帮助我，我将不胜感激。

Answer 1

这是我的示例代码，可以满足您的需求。

1. 为您的音频文件生成SAS令牌，并通过SAS令牌生成blob url，该音频文件通过适用于Python的Azure存储SDK通过命令pip install azure-storage安装。

   from azure.storage.blob.baseblobservice import BaseBlobService
   import numpy as np
   
   account_name = '<your account name>'
   account_key = '<your account key>'
   container_name = '<your container name>' # for example, `test`
   blob_name = '<your blob name>' # for example, `whatstheweatherlike.wav`
   
   blob_service = BaseBlobService(
       account_name=account_name,
       account_key=account_key
   )
   
   from azure.storage.blob import BlobPermissions
   from datetime import datetime, timedelta
   import requests
   
   sas_token = blob_service.generate_blob_shared_access_signature(container_name, blob_name, permission=BlobPermissions.READ, expiry=datetime.utcnow() + timedelta(hours=1))
   print(sas_token)
   url_with_sas = blob_service.make_blob_url(container_name, blob_name, sas_token=sas_token)
   print(url_with_sas)
   

2. 读取音频文件的Blob URL的内容，然后调用Azure语音到文本REST API，请参考正式文档Speech-to-text REST API。在这里，我使用了一个名为whatstheweatherlike.wav的官方音频样本，您可以从GitHub Repo samples/csharp/sharedcontent/console/whatstheweatherlike.wav的Azure-Samples/cognitive-services-speech-sdk中获得该样本。

   import requests
   
   subscription_key = '<your subscription key>'
   service_region = '<your service_region>' # for example, `eastasia`
   
   def get_token(subscription_key, service_region):
       fetch_token_url = f"https://{service_region}.api.cognitive.microsoft.com/sts/v1.0/issuetoken"
       headers = {
           'Ocp-Apim-Subscription-Key': subscription_key
       }
       response = requests.post(fetch_token_url, headers=headers)
       access_token = str(response.text)
       return access_token
   
   access_token = get_token(subscription_key, service_region)
   #print(access_token)
   
   endpoint = f"https://{service_region}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=en-US"
   
   audio_blob_url_with_sas = url_with_sas # it's from STEP 1.
   r = requests.get(audio_blob_url_with_sas)
   
   headers = {
       'Accept': 'application/json;text/xml',
       'Content-Type': 'audio/wav; codecs=audio/pcm; samplerate=16000',
       'Authorization': f"Bearer {access_token}" # Or just use `'Ocp-Apim-Subscription-Key': subscription_key` instead of `'Authorization'`
   }
   
   res = requests.post(endpoint, headers = headers, data = r.content)
   print(res.text)
   

最后，得到的结果如下。

{"RecognitionStatus":"Success","DisplayText":"What's the weather like?","Offset":300000,"Duration":13600000}