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 Aug 3, 2026Nemotron Speech Streaming is a tiny downloadable speech-to-text model from NVIDIA built for speed over accuracy. It processes an hour of audio in about three seconds, though it mishears roughly one word in seventeen on average.
Pick this for real-time transcription where latency matters more than perfect accuracy, or for financial calls and clean read-aloud scenarios where it scores under 2.7% error. Use it for edge deployment where a tiny parameter count keeps memory minimal. Skip it if you need commercial hosting, work with heavily accented or meeting audio, or require a permissive licence.
The case for it
- Extremely fast transcription at 1,071 times real time — an hour of audio in roughly 3.4 seconds on benchmark hardware.
- Strong on clean, structured audio: under 2% error on read speech and under 2.7% on financial calls.
- 0.6B total parameters, small enough for edge devices and tight memory constraints.
The case against it
- Accuracy collapses on challenging audio: more than six times the error rate on accented speech compared with clean read, and nearly five times in meetings.
- No commercial hosting available; you must self-host.
- Custom open-restricted licence, not Apache or MIT, which limits adoption.
How good is it?
TranscriptionTurning speech into text3 of 5Open ASR WER · 35th of 74
94.3%
Misses roughly one word in 17, averaged over nine English test sets.
1,071×23rd of 62
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, not to the board.
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.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
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?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
When we formed this view
Dates behind this page
Prices last checked 6h ago
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
- Modality record
- audio->text
- Catalogue slug
- nvidia-nemotron-speech-streaming-en-0-6b