Posted On: Oct 20, 2021

We are pleased to announce that Amazon Transcribe will now support custom language models (CLM) for streaming transcription. Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for you to add speech-to-text capabilities to your applications. CLM allows you to leverage pre-existing data to build a custom speech engine tailored for your transcription use case. No prior machine learning experience required. 

Live streaming transcription is used across industries in contact center applications, broadcast events, and e-learning. CLM enables you to improve the transcription accuracy by leveraging the text data, such as website content or instruction manuals, which covers your industry’s unique lexicon and vocabulary. To get started, just upload your training data set to train your CLM. Next, simply run transcription jobs using your new CLM. 

CLM for streaming transcriptions is available in US English and is available in AWS Regions where Amazon Transcribe streaming is supported, including US East (N. Virginia), US East (Ohio), US West (Oregon), South America (São Paulo), Asia Pacific (Seoul), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), EU (Frankfurt), EU (Ireland), and EU (London). For more details about the CLM feature, read our blog post “Building custom language models to supercharge speech-to-text performance for Amazon Transcribe” or visit the Amazon Transcribe documentation page