Sold by: Amazon Web Services
Deployed on AWS
This is a Machine Translation model built upon a Transformer model from Hugging Face.
Overview
This is a Machine Translation model built upon a Transformer model from Hugging Face . It takes a text string as input and predicts its translation.
Highlights
- This is a Machine Translation model from Hugging Face: https://huggingface.co/Helsinki-NLP/opus-mt-en-vi
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimensions summary
This model translates English text to Vietnamese, and the software carries no charge. You pay only for the compute you use. Pricing splits into two modes: real-time inference for live requests and batch inference for bulk processing. Within each mode, you choose an instance type sized by CPU, memory, or GPU capacity. Standard instances handle general workloads, while GPU-backed instances suit heavier processing. Real-time mode offers seven instance choices; batch mode offers six. All dimensions bill per host hour, so cost scales with the instance size you pick and how long it runs.
Top-of-mind questions for buyers
One HostHrs unit is one hour that a single inference instance runs. Billing counts each hour the chosen instance type stays active. If you run two instances, each accrues its own host hours. Cost tracks running time, so a longer-running instance adds more host hours to your bill.
Real-time mode keeps an instance running to answer live translation requests as they arrive. Batch mode processes bulk translation jobs and bills only while the job runs. Real-time suits continuous, on-demand traffic. Batch suits large, scheduled workloads. Both bill per host hour on the instance type you pick.
The software carries no charge, so no software fee applies. Instance charges accrue per host hour while the instance runs. A stopped instance stops accruing host hours. Underlying AWS infrastructure fees may still apply separately for storage or other resources tied to the instance.
huggingface.co
Helpful?
Vendor refund policy
None
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
This CPU version supports model run on CPU instance types
Additional details
Inputs
- Summary
The input is a text string.
- Input MIME type
- application/x-text
https://github.com/aws-samples/aws-marketplace-machine-learning/blob/master/using_open_source_model_packages/HF_translation_model/input_example
https://github.com/aws-samples/aws-marketplace-machine-learning/blob/master/using_open_source_model_packages/HF_translation_model/input_example
Resources
Vendor resources
Support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
This is a Machine Translation model built upon a Transformer model from Hugging Face.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.