State of Speech: New Data Report Reveals ASR’s Untapped Potential

BACK TO CHANGELOG

API, Speech Model

Updated General Model (English US)

BY Natalie Rutgers  | February 10 2021

model=general
version=2021-02-10.0

We have done additional training to our main General Model for US English to improve accuracy and expand the model vocabulary.  We’ve also incorporated our latest improvements to punctuation (punctuate=true).

The general model is Deepgram’s default model selection, but can also be called by passing model=general as an API parameter in your request. If you do not wish to use the latest version, be sure to specify the desired version as version={desired_version}.

Previous versions include:

  • 2020-11-24.0

 

Learn about opting in to General Releases. To get early access to updated base models, use model={desired_model}&version=beta.

Read more about selecting models and versions in the Deepgram Documentation.

Deepgram support, support@deepgram.com, is always available to help walk customers through new feature purpose and configuration, as well as resolve any issues that arise when upgrading.

Finally, a reason to get excited about voice recognition.

Check out Deepgram

Contact Us

Speech recognition is hard. We'll make it easy.