Niagara 19m Batch.en
Applied Brain Research · released Nov 13, 2025 · abr-ai/niagara-19m-batch.en
Speech to textTranscribes a recording into words
- Type
- Open weightsCustom licence
- Languages
- 1
- Size
- 20M
Context measured in tokens
Our take
Written Aug 3, 2026Niagara 19m Batch.en is a tiny English speech-to-text model built for speed over accuracy. It processes audio at thousands of times real time and fits on the smallest hardware, but only handles English and struggles with conversational audio.
Pick this for batch transcription of clean financial calls or read-aloud audio where speed matters most. Use it in speed-critical offline pipelines or for edge deployment where memory is tight. Skip it if you need multiple languages, are transcribing meetings or podcasts, or want hosted inference without setting up your own hardware.
The case for it
- Extremely fast batch transcription at 3,735 times real time — an hour of audio in under a second on benchmark hardware.
- Strong on clean, domain-specific audio: 3.86% word error rate on financial calls, 4.45% on clean read speech.
- Very small footprint with 20 million parameters, suitable for edge or embedded deployment.
The case against it
- Struggles with conversational and accented audio: 16.71% word error rate on recorded meetings, nearly four times worse than its clean-read performance.
- English only with no hosted inference; users must self-host under a custom restricted licence.
How good is it?
TranscriptionTurning speech into text1 of 5Open ASR WER · 69th of 74
90.1%
Misses roughly one word in 10, averaged over nine English test sets.
3,735×11th of 62
an hour of audio in under a second, 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, 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. 21.6 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. 22.8 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. 4.8 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 →
Models people weigh against Niagara 19m Batch.en
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
- abr-ai/niagara-19m-batch.en
- Architecture
- Dense
- Modality record
- audio->text
- Catalogue slug
- abr-ai-niagara-19m-batch-en