ARK ASR 0.6B
AutoArk AI · released May 25, 2026 · AutoArk-AI/ARK-ASR-0.6B
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 19
- Size
- 1.3B
about 25K words of context
Our take
Written Sep 11, 2026ARK ASR is a tiny downloadable speech-to-text model from AutoArk AI that handles 19 languages under a permissive Apache licence. It is unusually capable on messy real-world audio such as podcasts and meeting recordings, despite its modest size.
Pick this for transcribing podcasts, video, or meeting-room audio with crosstalk and distant microphones, where it outperforms most alternatives. Use it for accented English from non-native speakers, or for local deployment on edge hardware where a 1.3-billion-parameter footprint matters. Skip it if you need a hosted API, if your audio is clean read-aloud where it sits below the median, or if you need verified accuracy outside English.
The case for it
- Strong on messy real-world audio for its size: podcasts and video at 7.37%, meetings at 8.61%, both better than most models tracked.
- Extremely fast: 663 times real time on benchmark hardware, or roughly an hour of audio in five seconds.
- Apache 2.0 licence allows commercial use, modification and redistribution.
- Compact enough for edge and local deployment at 1.3 billion parameters.
The case against it
- Mediocre on clean read-aloud audio at 1.48%, slightly worse than the median across models tracked.
- No hosted API available; you must self-host.
- Error rate rises several-fold on harder audio, as with every model: from 1.48% on clean speech to 8.61% on meetings.
How good is it?
An open speech-to-text model for turning recordings of speech into written text.
- turning spoken English into written textOpen ASR WER · 18th of 76
- transcribing podcasts and video audioPodcasts and video · 11th of 92
TranscriptionTurning speech into text4 of 5Open ASR WER · 18th of 76
95.4%
Misses roughly one word in 22, averaged over nine English test sets.
663×44th of 74
an hour of audio in 5 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; the placing beneath each rate is against every model measured on that set.
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.
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. 20.7 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. 21.9 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. 3.9 GB spare means a 10% error in the size would not change the answer.
These cards answer whether ARK ASR 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.
Models people weigh against ARK ASR 0.6B
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 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-0.6B
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- autoark-ai-ark-asr-0-6b