FunClip
FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.
Runssource: GitHubhomepagePythonMITcommit 2a954d4fbad6
Python, MIT licensed. The project labels itself: ai tools, ai video editing, asr, auto subtitles, chinese, content creation, funasr and funclip.
FunClip runs. An Argusic agent installed it in 8.2 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
FunClip v2.2.1 is fully installed in a Python 3.12 venv with all dependencies, all 90 tests pass, the CLI recognition+clipping pipeline processes a real video with Paraformer-Large ASR and produces valid clipped MP4 output, and the Gradio web interface launches and serves HTTP 200 on localhost.
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.
- litellm and pytest missing from requirements.txt but required by tests0.5 minutes
- Gradio 4.44.1 has a json_schema_to_python_type crash on / route0.3 minutes
- videoclipper.py CLI stage 2 crashes with AttributeError: no 'lang' attribute0.2 minutes
- Debian's PEP 668 prevents system-wide pip install; must use a venv0.1 minutes
- Install time
- 8 minutes
- Cold machine to finish
- 49 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- cd /work/repo && /tmp/funclip_venv/bin/python -m pytest tests/ -q => 89 passed, 1 skipped, 0 failed. cd /work/repo && mkdir -p output && /tmp/funclip_venv/bin/python funclip/videoclipper.py --stage 1 --file examples/2022云栖大会_片段.mp4 --output_dir ./output => produces total.srt, recog_res_raw, timestamps. cd /work/repo && /tmp/funclip_venv/bin/python funclip/videoclipper.py --stage 2 --file examples/2022云栖大会_片段.mp4 --output_dir ./output --dest_text '所以这个是我们办这个奖的初心' --start_ost 0 --end_ost 100 --output_file ./output/res.mp4 => produces valid res_no0.mp4 (ffmpeg -v error -i produced zero stderr). GRADIO_ANALYTICS_ENABLED=False /tmp/funclip_venv/bin/python funclip/launch.py --port 7870 => curl -s -o /dev/null -w 'HTTP %{http_code}' http://127.0.0.1:7870/ returned HTTP 200
- Model tokens used
- 1,107,130
- Exact commit tested
- 2a954d4fbad6
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 3, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html 89 passed, 1 skipped, 11 warnings, 4 subtests passed in 6.09s Now let me compile the final result. Let me get the install timing: exec /bin/sh -lc "pip_install_start=\"13:16\"; pip_install_end=\"13:20\"; echo \"Install roughly 4 minut… succeeded in 0ms: Install roughly 4 minutes for deps, ~4 minutes for model downloads True Now I have a comprehensive picture. Let me produce the final report. tokens used 1,107,130 Now I have a comprehensive picture. Let me produce the final report.
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.
- Recovered from all 4 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.
- Measured 3 times, so the result is not a one-off.
What did not, or is not known
- Took 8.2 minutes to install, slower than the median of the 26 comparable projects Argusic has measured.
Of the 27 ai-tools projects Argusic has installed and timed, FunClip was the 17th fastest to reach a running state, and 17 of 27 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 8.2 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)
ai-toolsai-video-editingasrauto-subtitleschinesecontent-creationfunasrfunclipgradiollmparaformerspeech-recognitionspeech-to-textsubtitles-generatortranscriptionvideo-editingvideo-processingvideo-subtitlesvideo-transcriptionwhisper-alternative
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/funclip)Questions
- Does FunClip run?
- Yes. FunClip runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test FunClip?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2a954d4fbad6. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test FunClip?
- The run that produced this verdict cost $0.28: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does FunClip take to install?
- 8.2 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 FunClip need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing FunClip?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does FunClip compare with the alternatives?
- Of the 27 ai-tools projects Argusic has installed and timed, FunClip was the 17th fastest to reach a running state, and 17 of 27 reached one at all.
- Where is the evidence for FunClip?
- All 3 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.