BHG Site Working

Rebuild workshop — not the public history site

Public site: Preview · Real · burrasa.net (live until cutover)

Prototypes: Burra in the News · Burra Digital Archive

Meeting transcription methodology

How to turn a BHG site walkthrough recording into notes, a transcript, stills, and glossary updates. First used on 28 August 2026. Follow this for later meetings; don’t skip the stills pass — audio alone mishears names and can’t see “this page”. Don’t publish until the sensitive-talk discussion has happened.

Spellings live in glossary. Extend that file as you correct; don’t invent a second glossary per meeting.


What you are producing

One folder per meeting: meetings/YYYY-MM-DD/.

FileJob
meeting-notes.mdThe reliable account: decisions, walkthrough, actions. Write from audio first, then rewrite from stills.
transcript.mdTimestamped diarized transcript. Evidence, not the cleaned story. Light ASR fixes only.
screenshot-timestamps.jsonInclusive grab list {id, t, cue} for extraction.
screenshot-timestamps.mdSame list, human-readable.
stills/JPEGs NNN_HHMMSS.jpg. Working files; prefer not to commit.
phone-stills/JPEGs taken on the phone during the meeting (books, cards, print-outs), not extracted from video. Prefer not to commit.
stills-catalog.mdWhat each cluster of frames actually shows (and what the camera missed). Include phone stills here.
extract_stills.pyOptional local copy; canonical script is <code>extract_stills.py</code> in this folder. Multiple clips need a clip field in the JSON (see 4 Sep).

Also: a row in the meetings index, and any new names/IA in the project glossary. After notes exist and the sensitive-talk discussion has happened, rebuild BHG Site Working (python scripts/build.py in bhgsite-working) so the meeting is on the workshop site.

Do not put in git: the video, extracted wav/mp3 chunks, API keys, or (unless asked) the JPEG stills.


1. Recording

Probe before transcribing:

ffprobe -v error -select_streams v:0 -show_entries stream=width,height,duration -show_entries stream_side_data=rotation -of json VIDEO.mp4

Note duration, rotation, and (if present) GPS / creation time for the notes header.


2. Audio → first transcript

Keys and models

POST https://openrouter.ai/api/v1/audio/transcriptions
model deepgram/nova-3
response_format=verbose_json
provider options: diarize, punctuate, utterances, smart_format.

Chunking

Long files fail or stall. Split to ~8-minute 16 kHz mono wav, then 64 kbps mp3 chunks.

ffmpeg -i VIDEO.mp4 -ac 1 -ar 16000 audio.wav
# then cut into ~480s mp3 pieces

Work in %TEMP%\bhg-meeting-YYYYMMDD\ (or similar). Combined JSON can stay there; only markdown lands in docs.

Speaker IDs

Deepgram labels reset every chunk. Speaker 3:1 is not the same person as Speaker 0:1.

Transcript conventions


3. First notes (audio only)

Write meeting-notes.md before stills:

This pass will be wrong on exact page titles, fake group names, and “this list”. That’s fine. You need the spine so the timestamp list has somewhere to hang.


4. Screenshot timestamps (inclusive)

Read the transcript and list every moment the screen might add information. If in doubt, include it.

Include when someone:

Skip only if the span is clearly not about the screen (long policy talk with no click). Even then, one still at the start of the span is cheap.

Times are on the video clock, same as the transcript. Grab a couple of seconds into the span — they click, then point.

Write both:

{"id": "001", "t": "00:00:08", "cue": "Recording starts; maps / settlement by period"}

and a markdown table. Dense is correct: the 28 Aug pass used 185 grabs on a 73-minute tape.


5. Extract stills

Canonical script: <code>extract_stills.py</code>.

python meetings/extract_stills.py --video "C:\path\to\VIDEO.mp4" --meeting "C:\path\to\docs\projects\bhg-site\meetings\YYYY-MM-DD"

It reads screenshot-timestamps.json, seeks with ffmpeg (-ss before -i), autorotates, scales to 900px wide, JPEG q=3.

Sanity-check rotation on one known screen moment before the full run (four variants: default, -noautorotate, transpose=1, transpose=2). Keep the variant where webpage text is horizontal.

JPEG file size is a proxy:

Size (this pipeline)Likely content
≳ 80 KBReadable monitor
~30–80 KBPartial screen / glare / angle
≲ 30 KBDesk, paper, clothing, covered lens

Don’t describe every dark frame. Catalog the large ones; sample the small ones to confirm they’re useless.


6. Look at the stills (this is the correction pass)

For each useful still, transcribe what is on the page:

Write stills-catalog.md in two lists:

  1. On the monitor — still id, time, what’s there.
  2. Camera off — don’t pretend you saw Tindale / Features / Mongolata if the frame is a jumper.

When the camera missed, check the rebuild HTML (bhgsite2026/source/...) for the page they named. Creek Street “Vanstone, Hinch” was recovered that way on 28 Aug.

If a still contradicts the transcript (“Cherry and Kidd” vs GURNEY and KNAGGS on screen), keep both: they may have scrolled, or named a nearby heading. Then grep the site — 28 Aug had both headings, and the formatting bug was duplicate HTML blocks.


7. Correct the transcript

Rules:

  1. Glossary wins for established spellings (Burra, Ngadjuri, Ian Auhl, Mary Warnes, Rosemary Ros, Cyndi’s List, Yorke Peninsula).
  2. The still / HTML wins over ASR when the page is in frame (Inc., plaque count, “Burra Family History Group”, book titles).
  3. Don’t “clean up” speech. Only fix tokens that are clearly misheard names, places, or titles.
  4. Record in the transcript header which fixes you applied.
  5. Never remap Speaker N:M to names in the body.

Typical Deepgram traps on this project (fix on sight):

ASR often saysPrefer
Barra, Borrow, Borough, BarrowBurra
WarrensWarnes (Mary Warnes / CWA)
Rosemary RossRosemary Ros
Cindy’s ListCyndi’s List
York PeninsulaYorke Peninsula
inkInc.
paperwork (People hub)People
Vanstown HinchVanstone, Hinch
Bard Community SchoolBurra Community School
hIan AuhlIan Auhl

Don’t “fix” a word into a glossary term unless the still or HTML supports it.


8. Improve the notes

Second pass on meeting-notes.md, driven by the catalog:

The notes remain the document you act on. The transcript stays the raw tape.


9. Sensitive and internal-only talk

The workshop site publishes notes and the transcript. That is a wider room than the people who were in Burra. After the notes and transcript exist, stop and discuss with Emlyn before publishing (rebuild of BHG Site Working, and any commit of those files). Do not skip this because the rest of the pipeline is green.

What to look for (from the 4 September pass; extend the list when a later tape shows a new class):

What to keep:

How to leave it out:

If unsure, leave it in the docs draft and ask. Fail closed: do not publish the meeting until that conversation has happened.


10. Glossary

After every meeting, add anything new to glossary:

Prefer one row per term. Don’t duplicate the meeting notes. The glossary is for the next transcript, not a second set of minutes.

Companion for Country names: the Ngadjuri language note in planning docs.


11. Index

Add a row to the meetings index. Link notes, stills catalog, glossary. Don’t link the video.


Order of work (checklist)

  1. Probe video; extract wav; chunk; Deepgram via OpenRouter.
  2. transcript.md with Speaker N:M + light Burra-class fixes.
  3. meeting-notes.md from audio (decisions / actions).
  4. Inclusive screenshot-timestamps.json + .md.
  5. Test one still’s rotation; extract all stills.
  6. stills-catalog.md (screen vs missed).
  7. Grep bhgsite2026 HTML for names the stills or ASR are unsure about.
  8. Correct transcript; rewrite notes from catalog.
  9. Update glossary + meetings README (workshop disk).
  10. Stop. Discuss sensitive / internal-only spans with Emlyn. Write published/ notes and transcript. Then publish to BHG Site Working and commit if asked.
  11. Leave video, temp audio, keys, and JPEGs out of the commit unless asked.

Worked examples

28 August 2026: 73 minutes, 185 grabs. Useful stills confirmed Preview URLs, Inc./plaques, Resources tiles, VIC price list, Goyder cemetery link text, Weddings duplicates, and the CHERRY/KIDD / GURNEY/KNAGGS / HINCH duplicate-block bug. Maps opening, Features, and Mongolata were almost all off-camera — those sections in the notes stay audio-only (plus HTML for Creek Street).

4 September 2026: four clips (~32 minutes of tape, with gaps) and five phone stills. The camera almost never found the monitor; the books, the 2017 booklet table, and the IREN card are why the stills pass still matters. Clip A talked through Resources publications and the workshop Useful Links inventory anyway.

21 September 2026: one 42-minute clip. Monitor for the first three minutes (BHG-005 ticket + Harvard Ask Barbara table); camera covered after that. Full tape in docs; working-site copy is published/.