Niagara 84m Batch.en
Applied Brain Research · released Sep 12, 2026 · abr-ai/niagara-84m-batch.en
Speech to textTranscribes a recording into words
- Type
- Open weightsCustom licence
- Languages
- 1
- Size
- 84M
Context measured in tokens · download allowed, licence restricts use
Our take
Written Sep 29, 2026Niagara 84m Batch.en is a speech-to-text model you can download and run yourself, built for bulk transcription where speed matters more than word accuracy. It is small enough for modest hardware, but on every kind of English audio we hold it transcribes worse than most of the field.
Reach for it when you have a long backlog of clear, single-speaker audio and want it turned around quickly on your own machine. Read the licence before you build a commercial product on it, because it puts conditions on commercial use and redistribution. Skip it if you need accurate transcription of accented speakers, meetings or everyday internet audio, or if you need any language other than English.
The case for it
- Fast enough to make a backlog practical: 1,928 times real time on the leaderboard's own hardware, an hour of audio in about 2 seconds there.
- Small enough to run yourself at 84 million parameters, so a modest machine is the realistic route rather than a host.
- You can download it and run it yourself, with the licence conditions the thing to read before you build on it.
The case against it
- Worse than most models on every kind of English audio we hold: 3.1% of words wrong on clean read-aloud recordings against a field middle of 1.5%, and 12% on meeting recordings against a middle of 10.3%.
- Overall accuracy sits in the bottom quarter of the field: 7.5% of words wrong on average across nine English test sets, against a field middle of 5.2%, and 66th of 76 on Open ASR WER as of 28 Sep 2026.
- English is the only language measured, so nothing here tells you how it handles anything else.
How good is it?
An open speech-to-text model for turning recordings into written text, though it trails most models on accuracy.
- turning spoken English into written textOpen ASR WER · 66th of 76
- transcribing speakers with a range of accentsAccented speech · 61st of 76
- transcribing podcasts and video audioPodcasts and video · 80th of 92
- transcribing clear recordings of people reading aloudClean read speech · 83rd of 92
TranscriptionTurning speech into text2 of 5Open ASR WER · 66th of 76
92.5%
Misses roughly one word in 13, averaged over nine English test sets.
1,928×28th of 74
an hour of audio in 2 seconds, on the board's own hardware. Your machine will differ.
1
Listed on the model card. The accuracy above is English only.
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. 21.5 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. 22.7 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. 4.7 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Niagara 84m Batch.en 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.
Models people weigh against Niagara 84m Batch.en
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
- abr-ai/niagara-84m-batch.en
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- abr-ai-niagara-84m-batch-en