March 10th, 2025
Batch Container
Real-Time Container
GPU Transcription Inference Container
GPU Translation Inference Container
Version 12.0.1 is now available for Batch Container, Real-Time Container, GPU Transcription Inference Container and GPU Translation Inference Container.
Fix for issue with transcription accuracy on non-speech audio in English.
Real-Time Container - Note that this fix reverts part (150-200ms) of the latency improvements for English transcription in the 12.0.0 release.
The following security vulnerabilities have been assessed with updated severity ratings from Ubuntu:
CVE-2024-3596 (libgssapi-krb5-2, libk5crypto3, etc.) – Medium (downgraded from High)
CVE-2021-4156 (libsndfile1) – Low (downgraded from High)
CVE-2025-27113 (libxml2) – Medium (downgraded from High)
CVE-2023-40889 (libzbar0) – Medium (downgraded from Critical)
These severity ratings are based on Ubuntu’s assessment, which more accurately reflects the impact on this environment. No immediate high-priority patches are required.
💡 GPU Transcription and GPU Translation - Inference Containers
GPU Inference Containers are released in sync with the Real-time/Batch containers they support. You should only rely on an Inference Container working with a Real-time/Batch container if it has the same version number.
For full details and a guide to implementation, see GPU Transcription Inference Container and GPU Translation Inference Container.