Posted On: Aug 6, 2020

We are delighted to announce the launch of Custom Language Models (CLM) for Amazon Transcribe. Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for you to add speech-to-text capabilities to your applications. Unlike the Custom Vocabulary feature, which enhances speech recognition for a discrete list of out-of-lexicon terms, CLM allows you to leverage pre-existing data to build a custom speech engine tailored for your transcription use case. Amazon Transcribe customers who operate in domains as diverse as law, finance, hospitality, insurance, and media all stand to benefit.

Using CLM is easy because it capitalizes on text data users already possess, such as website content, instruction manuals, and other assets that represent your domain of operation. Simply upload your training data set, initialize model development, and then run transcription jobs using the resultant custom model. Moreover, no prior machine learning experience is required to use CLM. The process is fully automated and requires minimal intervention.

At launch, CLM supports US English and is available in all AWS Regions where Amazon Transcribe operates. To start building your own custom speech recognition model, log in to the Amazon Transcribe service console. For more details about the CLM feature, visit the Amazon Transcribe documentation page.