Model reference · open weights

nemotron-speech-streaming-en

nemotron-speech-streaming-en is an open-weight audio or speech model from nvidia, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Licence fee required Audio nvidia 1 variants 200k downloads/mo
Request a licence + hosting quote All served models Not on the shared API today — deployed on request.

About

What nemotron-speech-streaming-en is

Nemotron ASR Streaming h1, h2, h3, h4, h5, h6 { color: #76b900; / NVIDIA green / font-weight: 700; } hr { border: none; border-top: 1px solid #e5e7eb; margin: 2rem 0; } / Improve list spacing / ul, ol { margin-top: 0.5rem; margin-bottom: 0.5rem; } / Badge alignment consistency / img { display: inline; vertical-align: middle; } [](#model-architecture) [!Note] June 4, 2026: New multilingual model released: NVIDIA Nemotron 3.5 ASR Streaming 0.6B extends this English streaming ASR model to 40 language-locales in a single 600M-parameter model. It supports language-ID prompt conditioning, optional automatic language detection, punctuation and capitalization, and configurable low-latency streaming chunk sizes. March 12, 2026: nemotron-asr-streaming was released with updated checkpoint (trained on larger corpora). For the older checkpoint released in January 2026, please refer to the nemotron-speech-streaming-jan2026 branch. Nemotron-ASR-Streaming is an English, streaming Automatic Speech Recognition (ASR) engineered to deliver high-quality English transcription across both low-latency streaming and high-throughput batch workloads. Developed by NVIDIA, this 600M parameter model transcribes speech into text with native support for punctuation and capitalization and offers runtime flexibility with configurable chunk sizes, including 80ms, 160ms, 560ms, and 1120ms. By leveraging the state-of-the-art Cache-Aware FastConformer-RNNT architecture, the model eliminates redundant overlapping computations common in traditional "buffered" streaming. This allows it to process only new audio chunks while reusing cached encoder context, significantly improving computational efficiency and minimizing end-to-end delay without sacrificing accuracy. It transcribes speech into the English alphabet, spaces, and apostrophes, with full support for punctuation and capitalization. Trained on the ASRSet, a massive dataset of approximately 250,000 hours of US English (en-US) speech, it is engineered to perform across diverse and challenging acoustic conditions. Why Choose nvidia/nemotron-asr-streaming? Native Streaming Architecture: Cache-aware design enables efficient processing of continuous a

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makernvidia
TypeAudio & music
Parameters (lead)618M
Variants1
Runs withnemo
Released2025-12-17
Popularity200k downloads / month
Likes613
LicenceCommercial licence needed

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
nemotron-speech-streaming-en-0.6b618MBF16~1.4 GBWeights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Automatic Speech RecognitionAMIWER (1.12s frame size)11.73
Automatic Speech RecognitionEarnings22WER (1.12s frame size)12.52
Automatic Speech RecognitionGigaspeechWER (1.12s frame size)9.66
Automatic Speech RecognitionLibriSpeech test-cleanWER (1.12s frame size)2.32
Automatic Speech RecognitionLibriSpeech test-otherWER (1.12s frame size)4.84
Automatic Speech RecognitionSPGI SpeechWER (1.12s frame size)2.97
Automatic Speech RecognitionTEDLIUMWER (1.12s frame size)3.5
Automatic Speech RecognitionVoxPopuliWER (1.12s frame size)7.97

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys nemotron-speech-streaming-en for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (nemotron-speech-streaming-en below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="nemotron-speech-streaming-en" -F file=@audio.mp3

Details

Languages, data & research

Trained / evaluated on

nvidia/Granary YTC Yodas2 LibriLight librispeech_asr fisher_corpus Switchboard-1 WSJ-0 WSJ-1 National-Singapore-Corpus-Part-1 National-Singapore-Corpus-Part-6 vctk voxpopuli europarl

Tags

nemo safetensors gguf nemotron_asr_streaming feature-extraction transformers speech-recognition cache-aware ASR automatic-speech-recognition streaming-asr speech audio FastConformer RNNT

Papers

Licence

Commercial licence needed

The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗

Sources

Weights & code

Want nemotron-speech-streaming-en on EU-owned hardware?

Request a licence + hosting quote See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms