Skip to main content
NVIDIA
nemo-speech.cpp
Container
NVIDIA
nemo-speech.cpp

A lightweight native C++ runtime for NVIDIA Nemotron Speech models built on ggml. Runs speech models in real time and batch mode across platforms and backends.

LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
--help
08/04/2026 12:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
/opt/nemo-speech/bin/riva_server
08/04/2026 12:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4EXPOSE
50051/tcp
08/04/2026 12:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
1000:1000
08/04/2026 12:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
PATH=/opt/nemo-speech/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/bin:/bin
08/04/2026 12:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NVIDIA_DRIVER_CAPABILITIES=compute,utility
08/04/2026 12:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NVIDIA_VISIBLE_DEVICES=all
08/04/2026 12:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
LD_LIBRARY_PATH=/opt/nemo-speech/lib:/usr/local/lib:/usr/local/cuda/lib64:/usr/local/cuda/targets/x86_64-linux/lib:/usr/local/cuda/targets/aarch64-linux/lib:/usr/local/nvidia/lib64:/usr/local/nvidia/lib:/usr/lib/aarch64-linux-gnu/nvidia:/usr/lib/aarch64-linux-gnu/tegra:/usr/lib/aarch64-linux-gnu/tegra-egl:/lib/x86_64-linux-gnu:/usr/lib/x86_64-linux-gnu:/lib/aarch64-linux-gnu:/usr/lib/aarch64-linux-gnu
08/04/2026 12:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
HOME=/home/nemo
08/04/2026 12:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
org.opencontainers.image.title=NeMo-Speech.cpp org.opencontainers.image.description=Lightweight NVIDIA speech inference runtime org.opencontainers.image.vendor=NVIDIA
08/04/2026 12:15 PM UTC

Modal Content

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.