A company is using Amazon SageMaker to build a machine learning (ML) model to predict...

Amazon Web Services MLS-C01 Question Answer

A company is using Amazon SageMaker to build a machine learning (ML) model to predict customer churn based on customer call transcripts. Audio files from customer calls are located in an on-premises VoIP system that has petabytes of recorded calls. The on-premises infrastructure has high-velocity networking and connects to the company's AWS infrastructure through a VPN connection over a 100 Mbps connection.

The company has an algorithm for transcribing customer calls that requires GPUs for inference. The company wants to store these transcriptions in an Amazon S3 bucket in the AWS Cloud for model development.

Which solution should an ML specialist use to deliver the transcriptions to the S3 bucket as quickly as possible?

Order and use an AWS Snowball Edge Compute Optimized device with an NVIDIA Tesla module to run the transcription algorithm. Use AWS DataSync to send the resulting transcriptions to the transcription S3 bucket.

Order and use an AWS Snowcone device with Amazon EC2 Inf1 instances to run the transcription algorithm Use AWS DataSync to send the resulting transcriptions to the transcription S3 bucket

Order and use AWS Outposts to run the transcription algorithm on GPU-based Amazon EC2 instances. Store the resulting transcriptions in the transcription S3 bucket.

Use AWS DataSync to ingest the audio files to Amazon S3. Create an AWS Lambda function to run the transcription algorithm on the audio files when they are uploaded to Amazon S3. Configure the function to write the resulting transcriptions to the transcription S3 bucket.

Explanation:

The company needs to transcribe petabytes of audio files from an on-premises VoIP system to an S3 bucket in the AWS Cloud. The transcription algorithm requires GPUs for inference, which are not available on the on-premises system. The VPN connection over a 100 Mbps connection is not sufficient to transfer the large amount of data quickly. Therefore, the company should use an AWS Snowball Edge Compute Optimized device with an NVIDIA Tesla module to run the transcription algorithm locally and leverage the GPU power. The device can store up to 42 TB of data and can be shipped back to AWS for data ingestion. The company can use AWS DataSync to send the resulting transcriptions to the transcription S3 bucket in the AWS Cloud. This solution minimizes the network bandwidth and latency issues and enables faster data processing and transfer.

Option B is incorrect because AWS Snowcone is a small, portable, rugged, and secure edge computing and data transfer device that can store up to 8 TB of data. It is not suitable for processing petabytes of data and does not support GPU-based instances.

Option C is incorrect because AWS Outposts is a service that extends AWS infrastructure, services, APIs, and tools to virtually any data center, co-location space, or on-premises facility. It is not designed for data transfer and ingestion, and it would require additional infrastructure and maintenance costs.

Option D is incorrect because AWS DataSync is a service that makes it easy to move large amounts of data to and from AWS over the internet or AWS Direct Connect. However, using DataSync to ingest the audio files to S3 would still be limited by the network bandwidth and latency. Moreover, running the transcription algorithm on AWS Lambda would incur additional costs and complexity, and it would not leverage the GPU power that the algorithm requires.

AWS Snowball Edge Compute Optimized

AWS DataSync

AWS Snowcone

AWS Outposts

AWS Lambda

Amazon Web Services MLS-C01 View All Questions