whisper-ctranslate2
Whisper command line client compatible with original OpenAI client based on CTranslate2.
Runssource: GitHubPythonMITcommit 7c06913255be
Python, MIT licensed. The project labels itself: openai , openai whisper, speech recognition, speech to text and whisper.
whisper-ctranslate2 runs. An Argusic agent installed it in 6 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
Installed in a venv; the CLI answers version 0.5.7, all 17 unit tests pass, and 6 of 7 e2e tests pass including real small/medium-model transcription of the bundled samples matched against reference outputs, with only diarization failing because it needs a real HuggingFace token and pyannote/torch.
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 93.3 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.
- av 19.0.1 removed the metadata_errors kwarg, breaking faster-whisper 1.2.1 audio decode (TypeError open() got unexpected keyword argument 'metadata_errors')3 minutes
- System pip install blocked by PEP 668 externally-managed environment1 minute
- e2e test_transcribe_diarization failed: HF_TOKEN unset and pyannote.audio/torch not installed for gated pyannote/speaker-diarization-community-1 model1 minute
- Install time
- 6 minutes
- Cold machine to finish
- 22 minutes
- Errors hit and fixed
- 3 hit, 2 fixed with no human help
- How the result was proved
- whisper-ctranslate2 --version returned 'whisper-ctranslate2 0.5.7'; nose2 -s tests returned 'Ran 17 tests ... OK'; nose2 -s e2e-tests returned 'Ran 7 tests ... FAILED (failures=1)'; whisper-ctranslate2 --model tiny --device cpu --compute_type float32 --output_dir /tmp/out2 --language en e2e-tests/gossos.mp3 exited 0 and wrote 5 output files
- Model tokens used
- 71,659
- Exact commit tested
- 7c06913255be
- 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.
final_state: "Installed in a venv; CLI answers 0.5.7, 17 unit tests and 6/7 e2e tests pass includin… install_minutes: I'll put the install-phase minutes. Let me say ~6. Let me write the final line. Must be plain text starting with ARGUSIC_RESULT: followed by JSON on s… Let me put a JSON with proper escaping. install_minutes: the install + dependency fixes took roughly 6 minutes (venv ~5s + pip install ~24s… minutes for errors: PEP668 ~1, av ~3, diarization ~0 (couldn't fix, but it's part of e2e runtime; r… Let me write it.I have completed the mission. Let me compile the final report. **Summary of what I did and observed:** - **Install**: System `pip` is blocked by PEP 668 (externally-managed environment), so I created a … - **Error 1 fixed**: The install pulled `av 19.0.1`, and running a real transcription failed with `… - **Real verification (tier1)**: `whisper-ctranslate2 --model tiny e2e-tests/gossos.mp3` downloaded… - **Tests**: `nose2 -s tests` → `Ran 17 tests ... OK`. `nose2 -s e2e-tests` → `Ran 7 tests ... FAIL…
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 6 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 3 errors during setup, 1 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 6 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)
openai-openai-whisperspeech-recognitionspeech-to-textwhisper
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/whisper-ctranslate2)Questions
- Does whisper-ctranslate2 run?
- Yes. whisper-ctranslate2 runs. Argusic installed and launched it on a clean machine in 6 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test whisper-ctranslate2?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7c06913255be. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test whisper-ctranslate2?
- 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 whisper-ctranslate2 take to install?
- 6 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 whisper-ctranslate2 need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing whisper-ctranslate2?
- 3 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.
- Where is the evidence for whisper-ctranslate2?
- 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.