Support Matrix#

These support matrices list the supported hardware and software requirements of Riva.

Riva Speech Skills 2.2.0#

Server Hardware#

Data Center#

The following table shows the supported hardware for Riva Speech Skills 2.2.0 on data center platforms.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any NVIDIA Volta(tm) or later GPU (NVIDIA Turing(tm) and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500 MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Embedded#

The following table shows the supported hardware for Riva Speech Skills 2.2.0 on embedded platforms.

Server Software#

Data Center#

The following table shows the supported software for Riva Speech Skills 2.2.0 on data center platforms.

Software Compatibility

Container

MIG (Multi Instance GPU)

  • On A100 and A30 platforms, MIG is supported provided enough vRam is available for the selected models.

Note

For further information on Ampere and MIG, refer to Ampere Architecture In-Depth:.

Docker

Note

For DGX users, refer to Preparing to use NVIDIA Containers.

TAO Toolkit

NeMo

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Embedded#

The following table shows the supported software for Riva Speech Skills 2.2.0 on embedded platforms.

Software Compatibility

Container

Docker

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quick Start package, which are also based on gRPC.

Riva Speech Skills 2.1.0#

Server Hardware#

Data Center#

The following table shows the supported hardware for Riva Speech Skills 2.1.0 on data center platforms.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any NVIDIA Volta(tm) or later GPU (NVIDIA Turing(tm) and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500 MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Embedded#

The following table shows the supported hardware for Riva Speech Skills 2.1.0 on embedded platforms.

Hardware Compatibility

Operating System

Riva server requires Linux aarch64.

GPU Model

Deployment Platforms:

Jetson SDK version

JetPack 4.6.1

Mic, Camera, and Headset

Microphone:

  • Linux AArch64 with a USB microphone (for example, a Logitech H390 USB computer headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

RAM requirement

  • ASR Models

    • ~2300 MB

  • NLP Models

    • ~1800 MB (with punctuation)

  • TTS Models

    • ~2100 MB

  • All Models combined

    • ~4500 MB

Server Software#

Data Center#

The following table shows the supported software for Riva Speech Skills 2.1.0 on data center platforms.

Software Compatibility

Container

MIG (Multi Instance GPU)

  • On A100 and A30 platforms, MIG is supported provided enough vRam is available for the selected models.

Note

For further information on Ampere and MIG, refer to Ampere Architecture In-Depth:.

Docker

Note

For DGX users, refer to Preparing to use NVIDIA Containers.

TAO Toolkit

NeMo

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Embedded#

The following table shows the supported software for Riva Speech Skills 2.1.0 on embedded platforms.

Software Compatibility

Container

Docker

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quick Start package, which are also based on gRPC.

Riva Speech Skills 2.0.0#

Server Hardware#

Data Center#

The following table shows the supported hardware for Riva Speech Skills 2.0.0 on data center platforms.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any NVIDIA Volta(tm) or later GPU (NVIDIA Turing(tm) and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500 MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Embedded#

The following table shows the supported hardware for Riva Speech Skills 2.0.0 on embedded platforms.

Hardware Compatibility

Operating System

Riva server requires Linux aarch64.

GPU Model

Deployment Platforms:

Jetson SDK version

JetPack 4.6

Mic, Camera, and Headset

Microphone:

  • Linux AArch64 with a USB microphone (for example, a Logitech H390 USB computer headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

RAM requirement

  • ASR Models

    • ~2300 MB

  • NLP Models

    • ~1800 MB (with punctuation)

  • TTS Models

    • ~2100 MB

  • All Models combined

    • ~4500 MB

Server Software#

Data Center#

The following table shows the supported software for Riva Speech Skills 2.0.0 on data center platforms.

Software Compatibility

Container

MIG (Multi Instance GPU)

  • On A100 and A30 platforms, MIG is supported provided enough vRam is available for the selected models.

Note

For further information on Ampere and MIG, refer to Ampere Architecture In-Depth:.

Docker

Note

For DGX users, refer to Preparing to use NVIDIA Containers.

TAO Toolkit

NeMo

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Embedded#

The following table shows the supported software for Riva Speech Skills 2.0.0 on embedded platforms.

Software Compatibility

Container

Docker

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quick Start package, which are also based on gRPC.

Riva Speech Skills 1.10.0 Beta#

Server Hardware#

The following table shows the supported hardware for Riva Speech Skills 1.10.0 Beta.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any NVIDIA Volta(tm) or later GPU (NVIDIA Turing(tm) and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500 MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Server Software#

The following table shows the supported software for Riva Speech Skills 1.10.0 Beta.

Software Compatibility

Container

MIG (Multi Instance GPU)

  • On A100 and A30 platforms, MIG is supported provided enough vRam is available for the selected models.

Note

For further information on Ampere and MIG, refer to Ampere Architecture In-Depth:.

Docker

Note

For DGX users, refer to Preparing to use NVIDIA Containers.

TAO Toolkit

NeMo

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quick Start package, which are also based on gRPC.

Riva Speech Skills 1.9.0 Beta#

Server Hardware#

The following table shows the supported hardware for Riva Speech Skills 1.9.0 Beta.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any NVIDIA Volta(tm) or later GPU (NVIDIA Turing(tm) and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500 MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Server Software#

The following table shows the supported software for Riva Speech Skills 1.9.0 Beta.

Software Compatibility

Container

MIG (Multi Instance GPU)

  • On A100 and A30 platforms, MIG is supported provided enough vRam is available for the selected models.

Note

For further information on Ampere and MIG, refer to Ampere Architecture In-Depth:.

Docker

Note

For DGX users, refer to Preparing to use NVIDIA Containers.

TAO Toolkit

NeMo

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quickstart package, which are also based on gRPC.

Riva Speech Skills 1.8.0 Beta#

Server Hardware#

The following table shows the supported hardware for Riva Speech Skills 1.8.0 Beta.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500 MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Server Software#

The following table shows the supported software for Riva Speech Skills 1.8.0 Beta.

Software Compatibility

Container

MIG (Multi Instance GPU)

  • On A100 and A30 platforms, MIG is supported provided enough vRam is available for the selected models.

Note

For further information on Ampere and MIG, refer to Ampere Architecture In-Depth:.

Docker

Note

For DGX users, refer to Preparing to use NVIDIA Containers.

NVIDIA TAO Toolkit

NVIDIA NeMo

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quickstart package, which are also based on gRPC.

Riva Speech Skills 1.7.0 Beta#

Server Hardware#

The following table shows the supported hardware for Riva Speech Skills 1.7.0 Beta.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Server Software#

The following table shows the supported software for Riva Speech Skills 1.7.0 Beta.

Software Compatibility

Container

MiG (Multi Instance GPU)

  • On A100 and A30 platforms MiG is supported provided enough vRam is available for the selected Models.

Note

For further information on Ampere and MiG, see Ampere Architecture In-Depth:.

Docker

Note

For DGX users, see Preparing to use NVIDIA Containers.

TAO

Nemo

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quickstart package, which are also based on gRPC.

Riva Speech Skills 1.6.0 Beta#

Server Hardware#

The following table shows the supported hardware for Riva Speech Skills 1.6.0 Beta.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Server Software#

The following table shows the supported software for Riva Speech Skills 1.6.0 Beta.

Software Compatibility

Container

Docker

Note

For DGX users, see Preparing to use NVIDIA Containers.

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quickstart package, which are also based on gRPC.

Riva Speech Skills 1.5.0 Beta#

Server Hardware#

The following table shows the supported hardware for Riva Speech Skills 1.5.0 Beta.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Server Software#

The following table shows the supported software for Riva Speech Skills 1.5.0 Beta.

Software Compatibility

Container

Docker

Note

For DGX users, see Preparing to use NVIDIA Containers.

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quickstart package, which are also based on gRPC.

Riva Speech Skills 1.4.0 Beta#

Server Hardware#

The following table shows the supported hardware for Riva Speech Skills 1.4.0 Beta.

Hardware Compatibility

Operating System

Riva server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Riva is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Server Software#

The following table shows the supported software for Riva Speech Skills 1.4.0 Beta.

Software Compatibility

Container

Docker

Note

For DGX users, see Preparing to use NVIDIA Containers.

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Skills Clients#

Riva skills clients do not require a local GPU and have minimal hardware requirements. Refer to grpc_docs for creating client bindings in your programming language. The python_api_docs section describes the prebuilt Python bindings included in the Riva Quickstart package, which are also based on gRPC.

Jarvis Speech Skills 1.3.0 Beta

Hardware#

The following table shows the supported hardware for Jarvis Speech Skills 1.3.0 Beta.

Hardware Compatibility

Operating System

Jarvis server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Jarvis is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+GB VRAM is recommended.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Software#

The following table shows the supported software for Jarvis Speech Skills 1.3.0 Beta.

Software Compatibility

Container

Docker

Note

For DGX users, see Preparing to use NVIDIA Containers.

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Jarvis Speech Skills 1.2.x Beta

Hardware#

The following table shows the supported hardware for Jarvis Speech Skills 1.2.0 Beta.

Hardware Compatibility

Operating System

Jarvis server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Jarvis is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Software#

The following table shows the supported software for Jarvis Speech Skills 1.2.0 Beta.

Software Compatibility

Container

Docker

Note

For DGX users, see Preparing to use NVIDIA Containers.

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Jarvis Speech Skills 1.1.0 Beta

Hardware#

The following table shows the supported hardware for Jarvis Speech Skills 1.1.0 Beta.

Hardware Compatibility

Operating System

Jarvis server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Jarvis is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Software#

The following table shows the supported software for Jarvis Speech Skills 1.1.0 Beta.

Software Compatibility

CUDA

Docker

Note

For DGX users, see Preparing to use NVIDIA Containers.

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Jarvis Speech Skills 1.0.x Beta

Hardware#

The following table shows the supported hardware for Jarvis Speech Skills 1.0.0 Beta.

Hardware Compatibility

Operating System

Jarvis server requires Linux x86_64.

GPU Model

Preferred Deployment Platforms:

Note

Jarvis is supported on any Volta or later NVIDIA GPU (Volta, Turing, and NVIDIA Ampere GPU architecture) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy.

Mic, Camera, and Headset

Microphone:

  • Linux x86 with USB microphone (for example, a Logitech H390 USB Computer Headset)

Headphones:

  • Logitech H340

  • Logitech H390

  • Microsoft LX3000

GPU Memory

  • ASR Models

    • Streaming Models: ~5600 MB

    • Non-streaming models: ~3100 MB

  • NLP Models

    • ~500MB per BERT model

  • TTS Models

    • ~3500 MB

  • Total

    • 16000 MB

Software#

The following table shows the supported software for Jarvis Speech Skills 1.0.0 Beta.

Software Compatibility

CUDA

Docker

Note

For DGX users, see Preparing to use NVIDIA Containers.

Helm

NVIDIA Driver

Note

For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.