NVIDIA ASR NIM Support Matrix#
This page describes the software and hardware that the NVIDIA ASR NIM supports.
Nemotron Transcribe has a separate runtime and precision compatibility matrix. Use the Nemotron Transcribe section instead of the general hardware, FP16, and RMIR requirements below for that NIM.
Hardware#
The NVIDIA ASR NIM requires an NVIDIA GPU with a Compute Capability of 8.0 or higher and at least 16 GB of VRAM. Ensure that the models you deploy do not exceed the available GPU memory.
GPU |
Precision |
|---|---|
A30, A100 |
FP16 |
H100 |
FP16, FP8 |
A2, A10, A16, A40 |
FP16 |
L4, L40, GeForce RTX 40xx |
FP16, FP8 |
GeForce RTX 50xx |
FP16 |
Blackwell RTX 60xx |
FP16 |
DGX Spark * |
FP16 |
WSL2-compatible models include support for all RTX 40xx GPUs and later.
Note
DGX Spark supports Parakeet 1.1B CTC English, Parakeet 1.1B RNNT Multilingual, and Nemotron ASR Streaming. Support for the Parakeet models was introduced in Riva ASR NIM Release 1.8.0. Refer to the separate Nemotron Transcribe matrix for its ARM64 runtime compatibility.
Software#
Linux operating systems (Ubuntu 22.04 or later recommended)
NVIDIA Driver >= 535
NVIDIA Docker >= 23.0.1
A Windows 11 operating system (Build 23H2 and later) that is supported using Windows Subsystem for Linux:
The minimum supported driver version is 570.
The minimum supported Linux distribution is Ubuntu 24.04.
The recommended container management tool is Podman.
Supported Models#
The NVIDIA ASR NIM microservice supports the following Nemotron ASR models.
The microservice requires an NVIDIA GPU with Compute Capability >= 8.0. It automatically downloads a pre-built model when available for the target GPU or generates an optimized model on-the-fly using the RMIR model.
Model |
Publisher |
WSL2 Support |
|---|---|---|
NVIDIA |
✅ |
|
NVIDIA |
✅ |
|
NVIDIA |
❌ |
|
NVIDIA |
❌ |
|
NVIDIA |
❌ |
|
NVIDIA |
❌ |
|
NVIDIA |
❌ |
|
NVIDIA |
❌ |
|
NVIDIA |
❌ |
|
NVIDIA |
❌ |
|
OpenAI |
❌ |
|
NVIDIA |
❌ |
|
NVIDIA |
❌ |
The environment variable NIM_TAGS_SELECTOR is used to specify the desired model and inference mode. It is specified as comma-separated key-value pairs. Some ASR models support different inference modes tuned for different use cases. Available modes include streaming low latency (str), streaming high throughput (str-thr), and offline (ofl). Setting the mode to all deploys all inference modes where applicable.
Note
Parakeet 0.6b CTC English (en-US) can use FP8 on supported hardware. Nemotron ASR Streaming uses INT8 for all profiles. Nemotron Transcribe serves BF16, FP8, or NVFP4 decoder checkpoints, depending on what the GPU supports; refer to Nemotron Transcribe. Other ASR models use FP16 unless explicitly noted.
Parakeet 0.6b CTC English#
To use this model, set CONTAINER_ID to parakeet-0-6b-ctc-en-us . Choose a value for NIM_TAGS_SELECTOR from the following table as needed. For further instructions, refer to Launching the ASR NIM.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1 |
4.511 |
3.08 |
|
streaming |
1 |
4.676 |
3.07 |
|
offline |
1024 |
5.201 |
11.93 |
|
streaming |
1024 |
1.54 |
3.07 |
|
streaming-throughput |
1024 |
2.257 |
7.02 |
|
all |
1024 |
13.85 |
21.73 |
Note
Profiles with a Batch Size of 1 are optimized for the lowest memory usage and support only a single session at a time. These profiles are recommended for WSL2 deployment or scenarios with a single inference request client.
Speech Recognition with VAD and Speaker Diarization#
The profiles with silero and sortformer use Silero VAD to detect start and end of utterance and a four-speaker Sortformer model for speaker diarization. End of utterance detection using VAD is more accurate than the acoustic-model-based end of utterance detection that other profiles use. This profile is more robust to noise and generates fewer spurious transcripts than other profiles. It is also useful for applications where multiple speakers are present in the audio, such as call centers or meetings.
Standard English with Silero VAD & Sortformer Diarizer:
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
2.885 |
11.93 |
|
streaming-throughput |
1024 |
5.387 |
7.02 |
|
streaming |
1024 |
4.967 |
6.39 |
|
all |
1024 |
5.32 |
21.73 |
Parakeet 1.1b CTC English#
To use this model, set CONTAINER_ID to parakeet-1-1b-ctc-en-us. Choose a value for NIM_TAGS_SELECTOR from the following tables as needed. For further instructions, refer to Launching the ASR NIM.
This NIM includes automatic punctuation and capitalization. Punctuation is off by default. Enable it with --automatic-punctuation (CLI) or enable_automatic_punctuation=true (API). No additional model is required.
Standard English Speech Recognition#
The following table lists standard profiles for general English speech recognition.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
all |
1024 |
3.734 |
11.39 |
|
offline |
1024 |
2.248 |
5.83 |
|
streaming-throughput |
1024 |
2.512 |
5.05 |
|
streaming |
1024 |
2.19 |
4.13 |
Speech Recognition with VAD and Speaker Diarization#
The profiles with silero and sortformer use Silero VAD to detect start and end of utterance and a four-speaker Sortformer model for speaker diarization. End of utterance detection using VAD is more accurate than the acoustic-model-based end of utterance detection that other profiles use. This profile is more robust to noise and generates fewer spurious transcripts than other profiles. It is also useful for applications where multiple speakers are present in the audio, such as call centers or meetings.
Standard English with Silero VAD & Sortformer Diarizer#
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
2.917 |
12.82 |
|
streaming |
1024 |
2.758 |
7.23 |
|
streaming-throughput |
1024 |
2.657 |
7.87 |
|
all |
1024 |
9.632 |
47.22 |
Speech Recognition in True Offline Mode#
The profiles with true-ofl use Silero VAD to detect silences to segment long audio files into chunks of up-to 30s and then parallelize the inference for all chunks. This profile is useful for applications where the audios are long and the user wants to process it in offline fashion.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
2.761 |
17.59 |
Note
Parakeet 1.1b CTC English is supported on DGX Spark platform.
Parakeet 0.6b TDT#
Parakeet 0.6b TDT is a 600-million-parameter automatic speech recognition (ASR) model designed for high-quality transcription, featuring support for punctuation, capitalization, and accurate timestamp prediction.
These are the key features of this model:
Accurate word-level timestamp predictions
Automatic punctuation and capitalization
Robust performance on spoken numbers and song lyrics transcription
Model Types#
Parakeet-tdt-0.6b-v2 (type=default)
English-only model optimized for en-US transcription
Refer to Parakeet TDT 0.6B V2 for more details
Parakeet-tdt-0.6b-v3 (type=multi)
Multilingual model supporting 25 European languages
Refer to Parakeet TDT 0.6B V3 for more details
Supported Languages by Model Type#
Language |
Language Code |
Default |
Multi |
|---|---|---|---|
Bulgarian |
bg-BG |
✓ |
|
Croatian |
hr-HR |
✓ |
|
Czech |
cs-CZ |
✓ |
|
Danish |
da-DK |
✓ |
|
Dutch |
nl-NL |
✓ |
|
English (UK) |
en-GB |
✓ |
|
English (US) |
en-US |
✓ |
|
Estonian |
et-EE |
✓ |
|
Finnish |
fi-FI |
✓ |
|
French |
fr-FR |
✓ |
|
German |
de-DE |
✓ |
|
Greek |
el-GR |
✓ |
|
Hungarian |
hu-HU |
✓ |
|
Italian |
it-IT |
✓ |
|
Latvian |
lv-LV |
✓ |
|
Lithuanian |
lt-LT |
✓ |
|
Maltese |
mt-MT |
✓ |
|
Polish |
pl-PL |
✓ |
|
Portuguese |
pt-PT |
✓ |
|
Romanian |
ro-RO |
✓ |
|
Russian |
ru-RU |
✓ |
|
Slovak |
sk-SK |
✓ |
|
Slovenian |
sl-SI |
✓ |
|
Spanish |
es-ES |
✓ |
|
Swedish |
sv-SE |
✓ |
|
Ukrainian |
uk-UA |
✓ |
To use this model, set CONTAINER_ID to parakeet-0.6b-tdt. For further instructions, refer to Launching the ASR NIM.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
5.329 |
13.75 |
|
offline |
1024 |
5.681 |
14.02 |
Parakeet 1.1b RNNT Multilingual#
Parakeet 1.1b RNNT Multilingual model supports streaming speech-to-text transcription in multiple languages. Three model types are available, each optimized for different use cases.
Tip
This NIM includes automatic punctuation and capitalization. Punctuation is off by default. Enable it with --automatic-punctuation (CLI) or enable_automatic_punctuation=true (API). No additional model is required.
Model Types#
Default Type (type=default)
Supports automatic language detection - the model identifies the spoken language and provides the transcript accordingly
Model produces the detected language code as output.
Prompt Type (type=prompt)
Offers better accuracy compared to the default model
Does not support automatic language detection - language code must be passed from the client
Indic Type (type=indic)
Optimized for Indic languages
Supports automatic language detection but does not produce detected language code in output.
Supported Languages by Model Type#
Language |
Language Code |
Default |
Prompt |
Indic |
|---|---|---|---|---|
Arabic |
ar-AR |
✓ |
✓ |
|
Bengali (India) |
bn-IN |
✓ |
||
Czech |
cs-CZ |
✓ |
||
Danish |
da-DK |
✓ |
||
German |
de-DE |
✓ |
✓ |
|
English (UK) |
en-GB |
✓ |
✓ |
|
English (US) |
en-US |
✓ |
✓ |
✓ |
Spanish (Spain) |
es-ES |
✓ |
✓ |
|
Spanish (US) |
es-US |
✓ |
✓ |
|
French (Canada) |
fr-CA |
✓ |
||
French (France) |
fr-FR |
✓ |
✓ |
|
Hebrew |
he-IL |
✓ |
||
Hindi (India) |
hi-IN |
✓ |
✓ |
✓ |
Italian |
it-IT |
✓ |
✓ |
|
Japanese |
ja-JP |
✓ |
✓ |
|
Korean |
ko-KR |
✓ |
✓ |
|
Norwegian Bokmål |
nb-NO |
✓ |
||
Dutch |
nl-NL |
✓ |
||
Norwegian Nynorsk |
nn-NO |
✓ |
||
Polish |
pl-PL |
✓ |
||
Portuguese (Brazil) |
pt-BR |
✓ |
✓ |
|
Portuguese (Portugal) |
pt-PT |
✓ |
||
Russian |
ru-RU |
✓ |
✓ |
|
Swedish |
sv-SE |
✓ |
||
Tamil (India) |
ta-IN |
✓ |
||
Thai |
th-TH |
✓ |
||
Turkish |
tr-TR |
✓ |
Deployment Instructions#
To use this model, set CONTAINER_ID to parakeet-1-1b-rnnt-multilingual. Choose a value for NIM_TAGS_SELECTOR from the following table based on the model type needed. For further instructions, refer to Launching the ASR NIM.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
all |
1024 |
19.32 |
49.99 |
|
all |
1024 |
18.22 |
50.07 |
|
all |
1024 |
22.15 |
49.72 |
Speech Recognition with VAD and Speaker Diarization#
All profiles include Silero VAD to detect the start and end of utterances and a four-speaker Sortformer model for speaker diarization. End of utterance detection using VAD is more accurate than the acoustic-model-based end of utterance detection that other profiles use. This profile is more robust to noise and generates fewer spurious transcripts than other profiles. It is also useful for applications where multiple speakers are present in the audio, such as call centers or meetings.
Here are all the profiles available for each type:
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
7.381 |
25.56 |
|
streaming |
1024 |
7.061 |
12.83 |
|
streaming-throughput |
1024 |
7.216 |
14.75 |
|
all |
1024 |
19.32 |
49.99 |
|
offline |
1024 |
7.067 |
25.64 |
|
streaming |
1024 |
6.791 |
13.25 |
|
streaming-throughput |
1024 |
6.709 |
14.23 |
|
all |
1024 |
18.22 |
50.07 |
|
offline |
1024 |
8.303 |
25.75 |
|
streaming |
1024 |
8.195 |
12.83 |
|
streaming-throughput |
1024 |
8.043 |
14.35 |
|
all |
1024 |
22.15 |
49.72 |
Note
Parakeet 1.1b RNNT Multilingual is supported on Blackwell and DGX Spark platform.
Parakeet 0.6b CTC Vietnamese English#
Parakeet 0.6b CTC Vietnamese English code switch model supports streaming and offline speech-to-text transcription in Vietnamese + English with punctuations.
To use this model, set CONTAINER_ID to parakeet-ctc-0.6b-vi. Choose a value for NIM_TAGS_SELECTOR from the following table as needed. For further instructions, refer to Launching the ASR NIM.
Speech Recognition Base Profiles#
Base profiles use acoustic model based end of utterance detection.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
2.089 |
7.27 |
|
streaming |
1024 |
2.152 |
5.27 |
|
streaming-throughput |
1024 |
2.122 |
6.27 |
|
all |
1024 |
3.824 |
15.75 |
Speech Recognition Profiles with VAD and Speaker Diarization#
The profiles with silero and sortformer use Silero VAD to detect start and end of utterance and a four-speaker Sortformer model for speaker diarization. End of utterance detection using VAD is more accurate than the acoustic-model-based end of utterance detection that other profiles use. This profile is more robust to noise and generates fewer spurious transcripts than other profiles. It is also useful for applications where multiple speakers are present in the audio, such as call centers or meetings.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
2.698 |
13.47 |
|
streaming |
1024 |
2.504 |
7.58 |
|
streaming-throughput |
1024 |
2.635 |
8.28 |
|
all |
1024 |
5.207 |
26.24 |
Parakeet 0.6b CTC Mandarin English#
Parakeet 0.6b CTC Mandarin English code switch model supports streaming and offline speech-to-text transcription in Mandarin + English with punctuations.
To use this model, set CONTAINER_ID to parakeet-ctc-0.6b-zh-cn. Choose a value for NIM_TAGS_SELECTOR from the following table as needed. For further instructions, refer to Launching the ASR NIM.
Speech Recognition Base Profiles#
Base profiles use acoustic model based end of utterance detection.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
7.9 |
5.6 |
|
streaming |
1024 |
4.9 |
4.7 |
|
streaming-throughput |
1024 |
5.1 |
5.7 |
|
all |
1024 |
13.1 |
13.4 |
Speech Recognition Profiles with VAD and Speaker Diarization#
The profiles with silero and sortformer use Silero VAD to detect start and end of utterance and a four-speaker Sortformer model for speaker diarization. End of utterance detection using VAD is more accurate than the acoustic-model-based end of utterance detection that other profiles use. This profile is more robust to noise and generates fewer spurious transcripts than other profiles. It is also useful for applications where multiple speakers are present in the audio, such as call centers or meetings.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
5.6 |
11.5 |
|
streaming |
1024 |
5.0 |
6.7 |
|
streaming-throughput |
1024 |
5.1 |
7.4 |
|
all |
1024 |
14.2 |
22.9 |
Parakeet 0.6b CTC Taiwanese Mandarin English#
Parakeet 0.6b CTC Taiwanese Mandarin English code switch model supports streaming and offline speech-to-text transcription in Taiwanese/Mandarin + English.
To use this model, set CONTAINER_ID to parakeet-ctc-0.6b-zh-tw. Choose a value for NIM_TAGS_SELECTOR from the following table as needed. For further instructions, refer to Launching the ASR NIM.
Speech Recognition Base Profiles#
Base profiles use acoustic model based end of utterance detection.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
4.12 |
5.8 |
|
streaming |
1024 |
3.75 |
4.9 |
|
streaming-throughput |
1024 |
6.29 |
5.9 |
|
all |
1024 |
14.78 |
13.96 |
Speech Recognition Profiles with VAD and Speaker Diarization#
The profiles with silero and sortformer use Silero VAD to detect start and end of utterance and a four-speaker Sortformer model for speaker diarization. End of utterance detection using VAD is more accurate than the acoustic-model-based end of utterance detection that other profiles use. This profile is more robust to noise and generates fewer spurious transcripts than other profiles. It is also useful for applications where multiple speakers are present in the audio, such as call centers or meetings.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
5.21 |
12.03 |
|
streaming |
1024 |
4.78 |
6.95 |
|
streaming-throughput |
1024 |
4.06 |
7.68 |
|
all |
1024 |
12.93 |
23.91 |
Parakeet 0.6b CTC Spanish English#
Parakeet 0.6b CTC Spanish English code switch model supports streaming and offline speech-to-text transcription in Spanish + English with punctuations.
To use this model, set CONTAINER_ID to parakeet-ctc-0.6b-es. Choose a value for NIM_TAGS_SELECTOR from the following table as needed. For further instructions, refer to Launching the ASR NIM.
Speech Recognition Base Profiles#
Base profiles use acoustic model based end of utterance detection.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
8.05 |
5.2 |
|
streaming |
1024 |
9.9 |
4.5 |
|
streaming-throughput |
1024 |
5.3 |
8.0 |
|
all |
1024 |
13.1 |
12.5 |
Speech Recognition Profiles with VAD and Speaker Diarization#
The profiles with silero and sortformer use Silero VAD to detect start and end of utterance and a four-speaker Sortformer model for speaker diarization. End of utterance detection using VAD is more accurate than the acoustic-model-based end of utterance detection that other profiles use. This profile is more robust to noise and generates fewer spurious transcripts than other profiles. It is also useful for applications where multiple speakers are present in the audio, such as call centers or meetings.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
8.8 |
11.2 |
|
streaming |
1024 |
7.9 |
6.5 |
|
streaming-throughput |
1024 |
7.0 |
8.4 |
|
all |
1024 |
21.15 |
22.2 |
Conformer CTC Spanish#
To use this model, set CONTAINER_ID to riva-asr. Choose a value for NIM_TAGS_SELECTOR from the following table as needed. For further instructions, refer to Launching the ASR NIM.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
2 |
5.8 |
|
streaming |
1024 |
2 |
3.6 |
|
streaming-throughput |
1024 |
2 |
4.2 |
|
all |
1024 |
3.1 |
9.8 |
Canary 1b Multilingual#
Canary 1b is encoder-decoder model with a FastConformer Encoder and Transformer Decoder. It is a multi-lingual, multi-task model, supporting automatic speech-to-text recognition (ASR) and translation.
To use this model, set CONTAINER_ID to canary-1b. Choose a value for NIM_TAGS_SELECTOR from the following table as needed. For further instructions, refer to Launching the ASR NIM.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
6.5 |
13.4 |
Whisper Large V3 Multilingual#
Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation supporting multiple languages, proposed in the paper Robust Speech Recognition using Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. Refer to Whisper GitHub for more details.
To use this model, set CONTAINER_ID to whisper-large-v3. Choose a value for NIM_TAGS_SELECTOR from the following table as needed. For further instructions, refer to Launching the ASR NIM.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
offline |
1024 |
4.3 |
12.5 |
Nemotron ASR Streaming#
Nemotron ASR Streaming supports streaming speech-to-text transcription. Two model types are available, each optimized for different use cases.
Tip
This NIM includes automatic punctuation and capitalization. Punctuation is off by default. Enable it with --automatic-punctuation (CLI) or enable_automatic_punctuation=true (API). No additional model is required.
Model Types#
type=en-US: Optimized for English (US) speech-to-text transcription and the lowest latency profile for English-only deployments.type=multi: Supports automatic language detection across 40 language locales. Setlanguage_code=autoto have the model identify the spoken language, or pass a specific code (for example,fr-FR) to constrain decoding.
Nemotron ASR Streaming profiles with speaker diarization use the eight-speaker Sortformer model.
The max_speaker_count request value is an upper bound, so the model can return fewer speakers than the configured limit.
Parakeet CTC and Parakeet RNNT profiles use the older four-speaker Sortformer model.
For the full list of supported language codes, refer to Supported Languages by Model Type.
Supported Languages by Model Type#
The 40 locales in the type=multi variant are grouped into three tiers based on expected transcription quality:
Transcription-ready (19 locales): Highest-accuracy ASR, ready out of the box.
Broad-coverage (13 locales): Production ASR across an additional 13 locales.
Adaptation-ready (8 locales): Recognized by the tokenizer and designed for fine-tuning on in-domain data to unlock full transcription.
Language |
Language Code |
English Type |
Multilingual Type |
Tier |
|---|---|---|---|---|
Arabic |
ar-AR |
No |
Yes |
Transcription-ready |
Bulgarian |
bg-BG |
No |
Yes |
Broad-coverage |
Chinese (Simplified) |
zh-CN |
No |
Yes |
Broad-coverage |
Croatian |
hr-HR |
No |
Yes |
Broad-coverage |
Czech |
cs-CZ |
No |
Yes |
Broad-coverage |
Danish |
da-DK |
No |
Yes |
Broad-coverage |
Dutch |
nl-NL |
No |
Yes |
Transcription-ready |
English (UK) |
en-GB |
No |
Yes |
Transcription-ready |
English (US) |
en-US |
Yes |
Yes |
Transcription-ready |
Estonian |
et-EE |
No |
Yes |
Broad-coverage |
Finnish |
fi-FI |
No |
Yes |
Broad-coverage |
French (Canada) |
fr-CA |
No |
Yes |
Transcription-ready |
French (France) |
fr-FR |
No |
Yes |
Transcription-ready |
German |
de-DE |
No |
Yes |
Transcription-ready |
Greek |
el-GR |
No |
Yes |
Adaptation-ready |
Hebrew |
he-IL |
No |
Yes |
Adaptation-ready |
Hindi (India) |
hi-IN |
No |
Yes |
Transcription-ready |
Hungarian |
hu-HU |
No |
Yes |
Broad-coverage |
Italian |
it-IT |
No |
Yes |
Transcription-ready |
Japanese |
ja-JP |
No |
Yes |
Transcription-ready |
Korean |
ko-KR |
No |
Yes |
Transcription-ready |
Latvian |
lv-LV |
No |
Yes |
Adaptation-ready |
Lithuanian |
lt-LT |
No |
Yes |
Adaptation-ready |
Maltese |
mt-MT |
No |
Yes |
Adaptation-ready |
Norwegian Bokmål |
nb-NO |
No |
Yes |
Broad-coverage |
Norwegian Nynorsk |
nn-NO |
No |
Yes |
Adaptation-ready |
Polish |
pl-PL |
No |
Yes |
Broad-coverage |
Portuguese (Brazil) |
pt-BR |
No |
Yes |
Transcription-ready |
Portuguese (Portugal) |
pt-PT |
No |
Yes |
Transcription-ready |
Romanian |
ro-RO |
No |
Yes |
Broad-coverage |
Russian |
ru-RU |
No |
Yes |
Transcription-ready |
Slovak |
sk-SK |
No |
Yes |
Broad-coverage |
Slovenian |
sl-SI |
No |
Yes |
Adaptation-ready |
Spanish (Spain) |
es-ES |
No |
Yes |
Transcription-ready |
Spanish (US) |
es-US |
No |
Yes |
Transcription-ready |
Swedish |
sv-SE |
No |
Yes |
Broad-coverage |
Thai |
th-TH |
No |
Yes |
Adaptation-ready |
Turkish |
tr-TR |
No |
Yes |
Transcription-ready |
Ukrainian |
uk-UA |
No |
Yes |
Transcription-ready |
Vietnamese |
vi-VN |
No |
Yes |
Transcription-ready |
Note
For Nemotron ASR Streaming FP8 builds, set nn.use_trt_fp8=True and nn.fp8_manifest_path=<manifest_json>. Deployment on GPUs with compute capability below 8.9 fails by default; set nn.allow_trt_fp8_fallback=True only when FP16 fallback on those GPUs is acceptable.
Deployment Instructions#
To use this model, set CONTAINER_ID to nemotron-asr-streaming. Choose a value for NIM_TAGS_SELECTOR from the following table as needed. For further instructions, refer to Launching the ASR NIM.
Profile |
Inference Mode |
Batch Size |
CPU Memory (GB) |
GPU Memory (GB) |
|---|---|---|---|---|
|
streaming |
32 / 64 |
9 |
4 |
|
streaming |
128 / 1024 |
9 |
13 |
|
streaming |
512 / 4096 |
9 |
23 |
|
streaming |
32 / 64 |
9 |
4 |
|
streaming |
128 / 1024 |
9 |
12 |
|
streaming |
512 / 4096 |
9 |
21 |
Note
Nemotron ASR Streaming is supported on Blackwell and DGX Spark platforms.
Note
The batch_size=512 profile is optimized for maximum throughput and requires a GPU with at least 48 GB of memory during deployment. Although the profile might deploy on some 32 GB GPUs, the inference service can fail under peak load. Deploy this profile only on GPUs with at least 48 GB of memory.
Nemotron Transcribe#
Nemotron Transcribe serves offline recordings through JSON HTTP APIs.
Set CONTAINER_ID to nemotron-transcribe and use the image nvcr.io/nim/nvidia/nemotron-transcribe:1.0.0 (NGC catalog).
Refer to deployment and inference for commands.
There are three checkpoint profiles, selected by decoder precision.
The encoder and auxiliary pipeline are not converted by changing the precision selector.
concurrency=low and concurrency=high are runtime presets on these same profiles, not additional model downloads or prebuilt TensorRT engines.
Select the checkpoint with precision=nvfp4, precision=fp8, or precision=bf16, and the tier with concurrency=low (the default) or concurrency=high, for example NIM_TAGS_SELECTOR="precision=nvfp4,concurrency=high".
All profiles serve offline recordings.
The runtime selects compatibility by exact GPU compute capability and host architecture, not by the GPU marketing name or SM count. GPUs with tuned presets serve a measured configuration for each supported tier; other compatible GPUs plan the tier from total memory.
GPU |
Compute Capability, Host |
Decoder Precisions |
Concurrency Tiers |
Speculative Decoding |
|---|---|---|---|---|
A100 80 GB |
|
BF16 |
|
Not available |
L40S |
|
FP8; BF16 does not fit on one L40S |
|
Off by default |
H100, H200 (H200 is served by the H100 configuration) |
|
FP8 |
|
MTP by default; DFlash2 optional |
H100, H200 (H200 is served by the H100 configuration) |
|
BF16 |
|
Not available |
GH200 |
|
BF16, FP8 |
|
MTP by default; DFlash2 optional |
B200; GB200 on ARM64 |
|
BF16, FP8, NVFP4 |
|
MTP by default; DFlash2 not supported |
GB300 |
|
BF16, FP8, NVFP4 |
|
MTP by default; DFlash2 not supported |
B300 |
|
BF16, FP8, NVFP4 |
|
Off by default |
RTX PRO 6000 Blackwell (Workstation and Server Edition) |
|
NVFP4, FP8 |
|
MTP by default; DFlash2 optional |
RTX PRO 6000 Blackwell (Workstation and Server Edition) |
|
BF16 |
|
MTP by default; DFlash2 optional |
RTX PRO 5000 Blackwell |
|
NVFP4 |
|
Off by default |
Other RTX PRO Blackwell (not qualified) |
|
BF16, FP8, NVFP4 |
|
Off by default |
GeForce RTX 5090 |
|
NVFP4 |
|
Not available |
DGX Spark |
|
BF16, FP8, NVFP4 |
|
Off by default; MTP and DFlash2 optional |
A tier or speculative mode outside this table is reported as incompatible by list-model-profiles and refused at startup.
With Multi-turn Mode on (ASR_MULTI_TURN=on) or pipeline parallelism above 1, speculative decoding is off on every GPU; an explicit ASR_SALM_SPECULATIVE=mtp or dflash2 fails at startup.
“Planned” tiers size the decoder from total device memory instead of a measured preset.
Warning
Binary compatibility is not a claim that every GPU SKU, topology, precision, or workload is release-qualified. Use the validation record for your release when choosing production hardware. Other compute capabilities and host-architecture combinations are rejected.
Use Linux. The image is built on CUDA 13.4.1 and needs NVIDIA driver 615 or later. On NVIDIA data-center GPUs, a host with an older supported driver branch (535, 570, 580, 590, 595, or 610) runs the image through the CUDA forward-compatibility libraries included in the image; refer to CUDA Forward Compatibility. Forward compatibility does not apply to GeForce GPUs, and on NVIDIA RTX GPUs only to select NGC-Ready server SKUs; use driver 615 or later on those GPUs. Do not use the general ASR driver minimum above as a Transcribe requirement. WSL2 deployment is not qualified.
Memory requirements depend on precision, TP/PP topology, concurrency, graph capture, and audio duration.
The runtime plans against total device memory, not current free memory, and checks allocation during startup.
It does not guarantee a fixed whole-service memory footprint.
BF16 does not fit on a single L40S; a compatible precision alone does not establish memory feasibility.
Long recordings also use host RAM for the upload and the decoded audio; benchmark it with your longest recordings.
A planned high tier is sized from memory rather than from a measured preset; benchmark it on your workload.
The following table lists the measured peak GPU memory of the whole NIM.
GPU |
Decoder Precision |
One Stream, Minimum Settings |
|
|
|---|---|---|---|---|
RTX PRO 6000 Blackwell Workstation Edition (95.6 GiB) |
NVFP4 |
38.6 GiB |
69.1 to 75.6 GiB |
71.7 to 84.5 GiB |
RTX PRO 6000 Blackwell Workstation Edition (95.6 GiB) |
FP8 |
62.8 GiB |
63.5 to 73.0 GiB |
71.7 to 85.4 GiB |
Other GPUs and editions; BF16 |
Not measured |
Not measured |
Not measured |
Ranges cover one-hour recordings with word timestamps and speaker labels or in Multi-turn Mode, from 32 recordings in flight (four decoding at a time, the default long-audio limit) up to all lanes busy, and speculative decoding off, MTP, and DFlash2. They were measured with driver 595.99.02, which is below the driver requirement above for this GPU. For the measurement method, the minimum settings, and host memory, refer to GPU and Host Memory.
The recommended input is mono, 16 kHz PCM WAV audio, up to 3,600 seconds per request.
The supported audio formats are WAV, FLAC, and Ogg Opus.
Other audio and video formats are not supported and are refused.
Word timestamps and subtitles can be requested for all transcription languages; timing accuracy varies by language.
They are not supported with translation.
/v1/models lists the languages the model declares for transcription (transcribe) and translation (translate); this list is not a per-language accuracy qualification.
Translation is supported from any translate language into English and from English into any translate language; no other pairs are supported.
Translation is requested with an instruction, not a task value.
Supported Languages#
The model declares 40 transcription languages; 31 of them, including English, are also translation languages.
Pass the code, or a tag with that primary subtag such as fr-FR, in the language field (refer to Language).
Accuracy is published for English, German, French, Italian, Spanish, Portuguese, and Dutch on the Open ASR Leaderboard test sets; refer to Nemotron Transcribe Accuracy. For the other languages, validate on your own recordings.
Language |
Code |
Transcription |
Translation Into and out of English |
|---|---|---|---|
Arabic |
|
Yes |
Yes |
Armenian |
|
Yes |
No |
Bengali |
|
Yes |
No |
Bulgarian |
|
Yes |
Yes |
Chinese (Mandarin) |
|
Yes |
Yes |
Croatian |
|
Yes |
Yes |
Czech |
|
Yes |
Yes |
Danish |
|
Yes |
Yes |
Dutch |
|
Yes |
Yes |
English |
|
Yes |
Yes |
Estonian |
|
Yes |
Yes |
Filipino |
|
Yes |
No |
Finnish |
|
Yes |
Yes |
French |
|
Yes |
Yes |
German |
|
Yes |
Yes |
Greek |
|
Yes |
Yes |
Hebrew |
|
Yes |
No |
Hindi |
|
Yes |
Yes |
Hungarian |
|
Yes |
Yes |
Indonesian |
|
Yes |
Yes |
Italian |
|
Yes |
Yes |
Japanese |
|
Yes |
Yes |
Korean |
|
Yes |
Yes |
Latvian |
|
Yes |
Yes |
Lithuanian |
|
Yes |
Yes |
Maltese |
|
Yes |
No |
Norwegian Nynorsk |
|
Yes |
No |
Polish |
|
Yes |
Yes |
Portuguese |
|
Yes |
Yes |
Romanian |
|
Yes |
Yes |
Russian |
|
Yes |
Yes |
Slovak |
|
Yes |
Yes |
Slovenian |
|
Yes |
Yes |
Spanish |
|
Yes |
Yes |
Swedish |
|
Yes |
Yes |
Tamil |
|
Yes |
No |
Thai |
|
Yes |
Yes |
Turkish |
|
Yes |
No |
Ukrainian |
|
Yes |
Yes |
Vietnamese |
|
Yes |
No |
Speculative decoding uses the same checkpoint profiles; the tuned presets use MTP where the table lists it. Multi-turn Mode is off by default and serves without speculative decoding. Multi-turn Mode runs on one GPU and does not provide word timestamps. Refer to the API reference for request options and limitations.