onnx-asr
A lightweight Python package for Automatic Speech Recognition using ONNX models
Runssource: GitHubhomepagePythonMITcommit 675f0e68c24d
Python, MIT licensed. The project labels itself: asr, lightweight, onnx, parakeet, python, speech recognition, speech to text and stt.
onnx-asr runs. An Argusic agent installed it in 0.5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 249 core tests pass, package imports correctly, CLI displays help with all supported model names, and whisper-tiny model executes real ASR inference via Hugging Face.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- 6 preprocessors tests skipped: missing torch, onnx, kaldi_native_fbank (test-all deps, not core)
- onnxruntime pthread_setaffinity_np warnings in container
- Install time
- under a minute
- Cold machine to finish
- 12 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- pytest tests/onnx_asr/ exited 0, 249 passed (real HF model downloads, real inference); whisper-tiny loaded and recognized silence (empty result, expected); CLI --help prints all model options
- Model tokens used
- 33,251
- Exact commit tested
- 675f0e68c24d
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
2026-10-22 11:30:02.864217938 [E:onnxruntime:Default, env.cc:374 ThreadMain] pthread_setaffinity_np… 2026-10-22 11:30:02.867217876 [E:onnxruntime:Default, env.cc:374 ThreadMain] pthread_setaffinity_np… 2026-10-22 11:30:02.870209515 [E:onnxruntime:Default, env.cc:374 ThreadMain] pthread_setaffinity_np… 2026-10-22 11:30:02.873211004 [E:onnxruntime:Default, env.cc:374 ThreadMain] pthread_setaffinity_np… 2026-10-22 11:30:02.876208543 [E:onnxruntime:Default, env.cc:374 ThreadMain] pthread_setaffinity_np… Result: Good - the whisper-tiny model loaded from Hugging Face and ran inference on silence, returning an e… Here's the final summary: tokens used 33,251 Good - the whisper-tiny model loaded from Hugging Face and ran inference on silence, returning an e… Here's the final summary:
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 0.5 minutes, faster than the median of the 10 comparable projects Argusic has measured.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 11 asr projects Argusic has installed and timed, onnx-asr was the 1st fastest to reach a running state, and 8 of 11 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 0.5 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
asrlightweightonnxparakeetpythonspeech-recognitionspeech-to-textsttwhisper
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/onnx-asr)Questions
- Does onnx-asr run?
- Yes. onnx-asr runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test onnx-asr?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 675f0e68c24d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test onnx-asr?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does onnx-asr take to install?
- 0.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does onnx-asr need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing onnx-asr?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does onnx-asr compare with the alternatives?
- Of the 11 asr projects Argusic has installed and timed, onnx-asr was the 1st fastest to reach a running state, and 8 of 11 reached one at all.
- Where is the evidence for onnx-asr?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.