Deepgram released a new version of the self-hosted Speech Engine. Current on-prem customers may pull this version from Docker Hub as
or
. Improvements include:
Resolution of CVE-2021-3185 in a supporting library
Reliability improvements for real-time streaming
Improved logging for debugging
Better coordination of GPU and CPU resources in environments with multiple physical CPUs.
We’re excited to release this new functionality and will be happy to support you in your deployment!
Deepgram support is always available to help walk customers through new feature purpose and configuration, as well as resolve any issues that arise when upgrading.
Read more about Deepgram’s On-Prem Support in the Deepgram Documentation.