In order to transcribe audio files withe the whisper model I would assume that the asyn inference option on AWS sagemaker might be the right choice for long audio files (1 hour, around 5-50mb). According to the docs it should be possible to have payload sizes up to 1gb I followed philipp Schmids a…

Payload too large for Async Inference on Sagemaker

philhd June 9, 2023, 7:00am 8

depends on your inference script. you can try

"s3_location" : "path_to_s3"

Topic		Replies	Views
Deploying Open AI's whisper on Sagemaker Amazon SageMaker	54	16202	April 12, 2024
Async TEI Deployment Cannot Handle Requests greater than 2mb Amazon SageMaker	2	97	November 4, 2024
Curl parameters for aws-whisper-large inference end point? Amazon SageMaker	2	1123	October 17, 2022
Sagemaker serverless endpoint deployment error (Image size greater than support size)) Amazon SageMaker	3	1236	July 21, 2023
Using Inference API with large audio files Beginners	4	1185	September 16, 2022