Audio8 ASR 0.1B
AutoArk AI · released Jul 10, 2026 · AutoArk-AI/Audio8-ASR-0.1B
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution-NonCommercial 4.0
- Languages
- 7
- Size
- 0.3B
about 25K words of context · download allowed, licence restricts use
Our take
Written Sep 4, 2026Audio8 ASR is a tiny downloadable speech-to-text model from AutoArk AI that processes audio faster than almost anything we track — an hour of audio in about five seconds. Its accuracy lags behind most peers on every English condition measured, and the non-commercial licence limits where you can use it.
Pick this for offline batch transcription where raw speed beats accuracy, or for non-commercial projects that need a very small model running locally. Use it when its seven-language coverage matches your needs and you can tolerate roughly one word in fourteen wrong on English audio. Skip it if you need commercial use rights, hosted inference, or transcription quality near the middle of the field.
The case for it
- Extremely fast: processes an hour of audio in about five seconds on the benchmark rig.
- Very small at 0.3B total parameters, easy to run on modest hardware.
- Seven languages covered, including English, Chinese, French, Japanese, Cantonese, German and Korean.
The case against it
- Accuracy below most peers on every measured condition, from clean read speech through to recorded meetings.
- Non-commercial licence only: no commercial use or profit redistribution allowed.
- No hosted providers listed; you must run it yourself.
How good is it?
An open speech-to-text model for turning recordings into text, though it trails most models on accuracy.
- turning spoken English into written textOpen ASR WER · 65th of 76
- transcribing speakers with a range of accentsAccented speech · 66th of 76
- transcribing clear recordings of people reading aloudClean read speech · 81st of 92
TranscriptionTurning speech into text2 of 5Open ASR WER · 65th of 76
93%
Misses roughly one word in 14, averaged over nine English test sets.
719×41st of 74
an hour of audio in 5 seconds, on the board's own hardware. Your machine will differ.
7
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 ↓ ↑
English · Chinese · French · Japanese · Cantonese · German · Korean
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. 21.4 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. 22.6 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. 4.6 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Audio8 ASR 0.1B 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.
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 allowsCreative Commons Attribution-NonCommercial 4.0, 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
Creative Commons Attribution-NonCommercial 4.0
Weights are downloadable but commercial use is prohibited. Research and personal use only.
Identifiers
- Hugging Face
- AutoArk-AI/Audio8-ASR-0.1B
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- autoark-ai-audio8-asr-0-1b