ARK ASR 3B
AutoArk AI · released Jun 22, 2026 · AutoArk-AI/ARK-ASR-3B
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 19
- Size
- 4.1B
Context measured in tokens
Our take
Written Aug 2, 2026ARK ASR is a compact downloadable speech-to-text model from AutoArk AI that turns audio into written words. It is extremely fast on batch workloads and gets about one word in a hundred wrong on clean read-aloud audio, though its accuracy drops sharply on harder recordings.
Choose this for high-throughput offline transcription of clean, read-aloud audio where near-perfect accuracy matters, or for research and commercial projects that need a permissive licence. It is ideal when you can self-host and want to process large audio backlogs quickly. Skip it if you need hosted inference, are transcribing meetings or accented speech, or require verified accuracy in languages other than English.
The case for it
- Extremely fast: processes one hour of audio in about seven seconds on benchmark hardware.
- Strong on clean read-aloud speech, with about one word in a hundred wrong.
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- Nineteen declared languages including major East Asian and European ones.
The case against it
- Accuracy collapses on challenging audio: more than seven times worse on recorded meetings and general accented speech than on clean read-aloud.
- No hosted inference options in our catalogue; you must self-host.
- Every accuracy figure is English; no source we hold verifies the other eighteen languages.
How good is it?
TranscriptionTurning speech into text4.5 of 5Open ASR WER · 6th of 74
95.4%
Misses roughly one word in 22, averaged over nine English test sets.
484×40th of 62
an hour of audio in 7 seconds, on the board's own hardware. Your machine will differ.
19
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.
Which languages ↓ ↑
Chinese · English · German · Japanese · French · Korean · Spanish · Polish · Italian · Romanian · Hungarian · Czech · Dutch · Finnish · Croatian · Slovak · Slovenian · Estonian · Lithuanian
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. 18.9 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 26.9 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 2.1 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 ARK ASR 3B
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 allowsApache License 2.0, 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
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- AutoArk-AI/ARK-ASR-3B
- Architecture
- Dense
- Modality record
- audio->text
- Catalogue slug
- autoark-ai-ark-asr-3b