Yes. WhisperJAV runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 5 errors on the way, and recorded the session.

How did Argusic test WhisperJAV?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 982d5dd912f4. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test WhisperJAV?

The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does WhisperJAV take to install?

3 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 WhisperJAV need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing WhisperJAV?

5 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for WhisperJAV?

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.

WhisperJAV

ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV

Runssource: GitHub homepagePythonMITcommit 982d5dd912f4

Python, MIT licensed. The project labels itself: aitranslate, hallucination, japanese, llm, modelscope, qwen3, qwen3 asr and speech to text.

WhisperJAV runs. An Argusic agent installed it in 3 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.

Project installed from source at /work/repo with 79 packages in a Python 3.12 venv. All 4 verification commands pass: import, --version (1.9.3), --help (full CLI), --dump-params (safe config probe). 617/617 clean tests pass; 43 failures and 11 errors are pre-existing (version drift, restructured config, missing optional extras).
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 92 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 92 / 100
cost of the verifying run: $0.07 (measured)
recorded runs: 1
last tested: 2026-10-03
stars: 2,298
forks: 195
open issues: 104
watchers: 10
size: 44 MB
created: 2023-10-18
last push: 2026-09-17

Subject data from GitHub, linked at the top of this page, refreshed 2026-10-03. 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.

Time lost to each failure while testing WhisperJAV, drawn from the recorded run — Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

test_legacy.py: stale VAD version assertions (silero -> silero-v3.1)0.3 minutes
test_presets.py: asr_config.json restructured in v1.8.9, no longer has 'common_transcriber_options' section
test_acceptance_v1_8_7b0.py: version tests expect 1.8.7b0, actual is 1.9.3 (43 pre-existing failures, 11 errors)
Missing tkinter (system package) blocks test_simple_gap.py, test_tab_spacing.py
Missing PySubtrans (translate extra) blocks 10 tests

Install time: 3 minutes
Cold machine to finish: 11 minutes
Errors hit and fixed: 5 hit, 3 fixed with no human help
How the result was proved: python -m whisperjav.main --version -> 'WhisperJAV 1.9.3'. --dump-params -> config probe OK. 617/617 non-pre-existing tests passed, 43 pre-existing failures, 11 pre-existing errors.
Model tokens used: 131,865
Exact commit tested: 982d5dd912f4
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.

**Install:** Succeeded via `uv sync --extra cli` — 79 packages installed in ~3 minutes into a Pytho…
**Launch:** Succeeded — `python -m whisperjav.main --version` prints `WhisperJAV 1.9.3`, `--help` s…
**Tests:** 617 passed, 43 failed, 11 errors across the full non-slow/non-e2e suite. All failures ar…
1. **Version drift** — `test_acceptance_v1_8_7b0.py` asserts version `1.8.7b0` but the actual code …
2. **Restructured config** — `test_presets.py` references `asr_config.json` sections that were remo…
3. **Missing optional extras** — `PySubtrans` (translate extra, 10 tests) and `tkinter` (system pac…
**Fixed:** Updated two `silero` → `silero-v3.1` assertions in `test_legacy.py` that were failing on…
exec
/bin/sh -lc "echo \"ARGUSIC_RESULT:{\\\"install_succeeded\\\":true,\\\"launch_succeeded\\\":true,\\…
 succeeded in 0ms:
tokens used
131,865

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 3 minutes.
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

Hit 5 errors during setup, 2 of which were not solved.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

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 3 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

tested by	attempt	outcome	score	cost USD	when
Argusic Runner	1/3	Runs	92.00	0.07	2026-10-03 22:27 UTC

Topics (from GitHub)

aitranslate hallucination japanese llm modelscope qwen3 qwen3-asr speech-to-text speechenhancement subtitling ten-vad whisper zipformer

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/WhisperJAV.svg)](https://argusic.com/subject/whisperjav)

Questions

Does WhisperJAV run?: Yes. WhisperJAV runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test WhisperJAV?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 982d5dd912f4. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test WhisperJAV?: The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does WhisperJAV take to install?: 3 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 WhisperJAV need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing WhisperJAV?: 5 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for WhisperJAV?: 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.