Nemotron Speech Streaming en 0.6b
NVIDIA · released Dec 17, 2025 · nvidia/nemotron-speech-streaming-en-0.6b
Speech to textTranscribes a recording into words
- Type
- Open weightsCustom licence
- Size
- 0.6B
Context measured in tokens
Our take
Written Sep 17, 2026Nemotron Speech Streaming en 0.6b is a downloadable speech-to-text model from NVIDIA that is quick and solid on everyday internet audio, and weak on clean read-aloud and accented speech. We list no host for it, so running it yourself is the only route we can point you to.
Reach for it when you are working through podcasts, video or other everyday internet audio, where it beats most models on this page, or when you have a long backlog to clear. Read the custom licence before you build on it. Skip it if you need accurate transcription of clean read-aloud speech or of accented speakers, or if you would rather not run the model on your own machine.
The case for it
- Podcasts and video come out better than most models here, at 7.9% of words wrong against a field middle of 8.3%.
- Recorded meetings land at 8.8% of words wrong, better than most models here and well clear of the field's worst.
- An hour of audio in about 3 seconds on the leaderboard's own hardware, so a long queue of recordings becomes practical to work through.
The case against it
- Clean read-aloud speech is its weak spot: 1.9% of words wrong against a field middle of 1.5%, so it trails most models on the easiest audio.
- Accented speakers cost it accuracy, at 9.5% of words wrong against a field middle of 7.9%.
- The custom licence puts conditions on commercial use and redistribution, so it needs reading before you build on it.
How good is it?
An open speech-to-text model for turning recordings into written text, though it trails most models on clear read-aloud audio.
- transcribing clear recordings of people reading aloudClean read speech · 71st of 92
TranscriptionTurning speech into text3 of 5Open ASR WER · 39th of 76
94.8%
Misses roughly one word in 19, averaged over nine English test sets.
1,167×31st of 74
an hour of audio in 3 seconds, on the board's own hardware. Your machine will differ.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case; the placing beneath each rate is against every model measured on that set.
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
Each of these is the same transcription job on a different kind of recording, so together they say where it holds up and where it slips — not how closely it follows an instruction.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 21.2 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 22.4 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 4.4 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Nemotron Speech Streaming en 0.6b loads, not how fast it transcribes. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first. This is a fit answer: whether it loads, not how fast it transcribes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- nvidia/nemotron-speech-streaming-en-0.6b
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- nvidia-nemotron-speech-streaming-en-0-6b