AWS Transcribe gives an error for Arabic (ar-SA) with 8k Hz audio sample rate

Question

Hi
I can see AWS Transcribe support  Arabic (ar-SA) audio and it also supports audio with 8k Hz sample rate (as per this [link](https://docs.aws.amazon.com/transcribe/latest/dg/how-input.html)). However when I try to transcribe from  audio file which is PCM 8k Hz it gives me below error
"The audio sample rate 8000 Hz is not supported. Change the audio sample rate of your media file and try your request again"

The same audio format works fine for other languages but not for Arabic (ar-SA).
Any help/pointers on why this won't work?

Thanks

Accepted Answer

The limitation is mentioned in the API documentation as follows:

>  To transcribe speech in Modern Standard Arabic (ar-SA), your media file must be encoded at a sample rate of 16,000 Hz or higher.

* https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html#transcribe-StartTranscriptionJob-request-LanguageCode

Please use a sample rate of 16k Hz or higher for ar-SA.

Answer

Thanks very much Taka_M
I think I missed that part in the documentation

AWS Transcribe gives an error for Arabic (ar-SA) with 8k Hz audio sample rate

相關內容