Overview
This container makes it possible to quickly deploy a pretrained, english-language transcription model.
You can send any sample rate of WAV files, but they will be converted to 32kHz. Metadata is outputted as JSON.
This container uses Kaldi, an open-source speech recognition toolkit written in C++ for speech recognition and signal processing, freely available under the Apache License v2.0.
For training data, it uses Librispeech. a corpus of approximately 1000 hours of read English speech with sampling rate of 16 kHz, prepared by Vassil Panayotov with the assistance of Daniel Povey. The data is derived from read audiobooks from the LibriVox project, and has been carefully segmented and aligned.
Highlights
- 3.29% Word Error Rate (WER)
- Data charges equate to approximately $0.01 per hour of audio, based on 32kHz mono WAV files and our charge of $0.04 per GB of received data.
- You can send any type of WAV file with any sample rate and bit depth. They'll be converted to 32kHz for our processing, and we'll send you the JSON.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Cost/MB |
|---|---|
25MB of received data | $0.001 |
Vendor refund policy
No refunds but you can cancel anytime
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
API
- Amazon EKS
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
We added the Nvidia NeMo feature.
Additional details
Usage instructions
No Setup is required. Just run the container image and it should all be working. The API will be available under the port 3000. You can access the documentation in your browser by requesting the route /api-docs. For example the url would be "http://localhost:3000/api-docs ", this will return all information about the API.
The container needs role permissions for metering to run which could be given by a role or the environment variables (ACCESS_KEY_ID, SECRET_ACCESS_KEY, AWS_REGION).
You if you're not using EKS or ECS, you can run the image using: docker run -p 3000:3000 $IMAGE_ID
Support
Vendor support
Request 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
