Deepgram released a new version of its on-premises solution.
On-Premises Release 220708 Docker Hub Images
deepgram/onprem-api:1.60.0
deepgram/onprem-engine:3.28.10
Minimum required NVIDIA driver version: >=450.80.02
deepgram/onprem-license-proxy:1.1.0
deepgram/onprem-billing:1.4.0
deepgram/onprem-metrics-server:2.0.0
This Release Contains The Following Changes
Deepgram On-premises now supports Enhanced models for ASR requests.
Enhanced models can be invoked on-prem by using the model=general-enhanced request parameter. At this time, on-prem does not support the new tier=enhanced syntax.
Transcription Find and Replace is now supported via the replace URI parameter. To learn more, please visit the feature page for Find and Replace.
The /v2/models endpoint response now includes the model UUID for cross-referencing against the model UUID listed in the /v2/listen response.
Compatibility Notice
Any [[post_processing_info.plugins]] sections defined in the api.toml file will need to be deleted to get properly formatted responses with this release.