Azure-docs: Possible to get transcription confidence?

[bensimon24]

Is it possible to get the confidence for a transcription using this method?

---

Document Details

⚠ Do not edit this section. It is required for docs.microsoft.com ➟ GitHub issue linking.

• ID: a421fddc-eebd-2ff2-6216-b2a00bbd3fdf
• Version Independent ID: 7d902f9e-4f56-30c9-4a39-7d800f92e088
• Content: Quickstart: Recognize speech from an audio file - Speech Service - Azure Cognitive Services
• Content Source: articles/cognitive-services/Speech-Service/quickstarts/speech-to-text-from-file.md
• Service: cognitive-services
• Sub-service: speech-service
• GitHub Login: @erhopf
• Microsoft Alias: erhopf

[ram-msft]

@bensimon24 Thanks for the question. We are investigating the issue and will update you shortly.

[ram-msft]

@bensimon24

Please follow the below link for getting the confidence score.
https://stackoverflow.com/questions/57043876/can-i-retrieve-the-confidence-of-the-transcription-from-azure-cognitive-services/57142560#57142560

[bensimon24]

Thank you for the reply. I was looking at that stack overflow post, and it looks like it was written for C#. Are there any examples for how to configure OutputFormat in python? Despite looking, I am unable to find the same functionality or an example in the python docs.

[rhurey]

Assuming you imported the Speech SDK as:
import azure.cognitiveservices.speech as msspeech
and your Speech Config object is named speech_config

You can set the property using:
speech_config.output_format = msspeech.OutputFormat.Detailed

[ram-msft]

@bensimon24 We will now proceed to close this thread. If there are further questions regarding this matter, please tag me in your reply. We will gladly continue the discussion and we will reopen the issue.