mathiasandClaude Opus 5
489b4bb2a1
analyze_srt.py, build_page.py and transcode.yaml produced the /bygge prototype. They were sitting in a session scratchpad on tmpfs, one reboot from gone, while spike issues #29-#31 were written as if they had to be built from scratch. Committed as found, defects documented rather than fixed: max_tokens=6000 truncates anything past ~6 minutes of audio, the page title is hardcoded, and the schema still carries fields no consumer renders. The four-check validator is the part worth keeping — the coverage-gap and Swedish-number-grounding checks catch errors that timestamp and citation checks structurally cannot. Real transcripts and analyses stay out: this repo is public and the recordings are a named person discussing a client's project. Only the synthetic fixture is committed, which exercises all four checks with no model call. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
73 lines
4.0 KiB
Markdown
73 lines
4.0 KiB
Markdown
# spike-media — the `/bygge` toolchain, recovered
|
||
|
||
Throwaway spike tooling for #28 (upload → transcript → takeaways). Committed
|
||
because it was found in `tmpfs` one reboot from gone, not because it is finished.
|
||
|
||
Nothing here is wired into tapir. No database, no HTTP handler, no ADR.
|
||
|
||
## What produced `/bygge`
|
||
|
||
The prototype at `tapir.d-ma.be/bygge` was **not** hand-built, which the epic and
|
||
the first round of spike issues both got wrong. It came from these three scripts:
|
||
|
||
```
|
||
IMG_1233.mov --transcode.yaml--> IMG_1233.web.mp4 (k3s Job, h264, +faststart)
|
||
IMG_1233.wav --whisper---------> IMG_1233.sv.srt (interactive — the one manual step)
|
||
IMG_1233.sv.srt --analyze_srt.py--> analys.json (berget/mistral-medium, temperature=0)
|
||
analys.json + video --build_page.py--> page HTML
|
||
```
|
||
|
||
The reference analysis was produced by **`berget/mistral-medium`** — a mid-tier
|
||
cloud model, not a frontier one. That matters when judging what a local model
|
||
has to clear: the bar is mistral-medium, and it should be re-run as the control
|
||
arm rather than excluded.
|
||
|
||
## The validator is the valuable part
|
||
|
||
`analyze_srt.py` grades its own output on four checks. Two of them catch classes
|
||
of error that timestamp- and citation-checking cannot:
|
||
|
||
| Check | Catches |
|
||
|---|---|
|
||
| citation exact / **partial** / absent | Paraphrase presented as a quote. Three tiers, because `alternativ` citations legitimately stitch non-contiguous passages — a strict substring test fails the reference output. |
|
||
| `TALET … FINNS INTE I CITATET` | A wrong number carried by a *verbatim* citation and a *real* timestamp. Converts Swedish number-words to digits first. It caught `45×230` where the transcript said `220`. |
|
||
| `TACKNINGSLUCKA` | Spans of the clip no section covers. **The recall term** — without it an empty analysis scores perfectly on every other check. |
|
||
| timestamp exists in the SRT | Fabricated seek targets. Near-solved: 74/75 on the reference, because the model copies the cue starts it was handed. |
|
||
|
||
## Known defects — read before running
|
||
|
||
- **`max_tokens: 6000` is too low.** The 4-minute reference analysis is ~4,700
|
||
output tokens, i.e. ~78% of budget. A 10-minute clip truncates for every model,
|
||
and truncation reads as a JSON-discipline failure if you are not counting
|
||
tokens. Record `finish_reason` and separate `truncated` from `malformed`.
|
||
- **`build_page.py` hardcodes the title** (`"Jonas – genomgång av tillbyggnad"`).
|
||
- **The schema carries fields nothing renders** — `projekt.sammanfattning`,
|
||
`projekt.skede`, `avsnitt.bildtid`, `avsnitt.bildmotiv`, `material[]`,
|
||
`oklart[]` — left over from an earlier still-frame/markdown output that
|
||
`build_page.py` replaced. They are paid for in output tokens on every run.
|
||
- **Speaker attribution is inferred, not diarized.** The output attributes
|
||
statements by name from an SRT with no speaker labels. All four checks above
|
||
are blind to a misattribution.
|
||
- **The web encode does not downscale.** The source is 720×1280; `-preset
|
||
veryfast -crf 24` on handheld motion is what makes it ~5 Mbps, not the
|
||
resolution. The lever is the preset.
|
||
|
||
## Fixtures
|
||
|
||
`fixtures/fake.sv.srt` + `fixtures/fake.analys.json` — a synthetic 7-cue Swedish
|
||
construction walkthrough with planted numbers. No real people, no real project.
|
||
It exercises the parser and all four validator checks **without a model call**,
|
||
which is what makes it usable in a test.
|
||
|
||
## Why the real artifacts are not here
|
||
|
||
**This repo is public.** The prototype's transcript and analysis are a verbatim
|
||
recording of a named person discussing a client's building project — private
|
||
third-party content, and exactly the class of data #28 calls out as the reason
|
||
uploaded transcripts cannot live in the shared `transcripts` table.
|
||
|
||
So `IMG_1233.sv.srt`, `payload.json` and the model-comparison runs stay out of
|
||
git here. That leaves `/bygge` without a versioned source of truth, which is a
|
||
real gap and a decision for #28: a private repo, an encrypted blob, or accepting
|
||
that the reference artifacts live outside version control.
|