open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 4 Activity

refactor(examples): replace sector-specific example material with generic, fictitious examples

Browse source 
Reference files, test fixtures, the playground demo project and one design
document now use generic, fictitious examples (buildings, energy, water,
grants, municipal services). The playground demo (17 fixtures plus the
embedded demo state) tells one consistent story: a municipal customer
chatbot that pre-screens housing-benefit applications, classified under
Annex III point 5(a). The embedded demo copies were edited in place rather
than regenerated, because they already carry newer AI Act dates than the
fixture files.

Legal text is unchanged. Test semantics are unchanged. Four dark-theme
onboarding screenshots with outdated placeholder text are removed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-23 14:03:53 +02:00
commit 544934dc57
Signed by: ktg
SSH key fingerprint: SHA256:JakMjO6FTBBzN0Bhfj9saOoEjaFxlSdYuZQQpM/lF9Q
77 changed files with 363 additions and 368 deletions
Download patch file Download diff file Expand all files Collapse all files

8
skills/ms-ai-engineering/references/multi-modal/speech-to-ai-pipelines.md
View file

@ -93,14 +93,14 @@ For norsk offentleg sektor med spesialisert terminologi:
| Tilpasning | Brukstilfelle | Eksempel |
|-----------|--------------|---------|
| **Phrase list** | Forbetra gjenkjenning av spesifikke ord | Stadnamn, fagtermar |
| **Custom model** | Trenar ny modell med eigne data | Vegsektoren, helsesektor |
| **Custom model** | Trenar ny modell med eigne data | Energisektoren, helsesektor |
| **Display format** | Tilpass visning av gjenkjend tekst | Tal-til-siffer, dato-format |
```python
# Phrase list for forbetra norsk gjenkjenning
phrase_list = speechsdk.PhraseListGrammar.from_recognizer(speech_recognizer)
phrase_list.addPhrase("Direktoratet for digital tjenesteutvikling")
phrase_list.addPhrase("E6 Megården-Mørsvikbotn")
phrase_list.addPhrase("Lofotodden nasjonalpark")
phrase_list.addPhrase("Utredningsinstruksen")
phrase_list.addPhrase("Forvaltningsloven")
phrase_list.addPhrase("personvernforordningen")
@ -217,9 +217,9 @@ class AudioPreprocessor:
Mikrofon → Audio stream → Azure Speech SDK
↓
┌── Recognizing event (interim)
│ "Eg trur at veg..."
│ "Eg trur at helse..."
├── Recognized event (final)
│ "Eg trur at vegsektoren bør investere meir."
│ "Eg trur at helsesektoren bør investere meir."
│ Offset: 1800000 ticks
│ Duration: 30500000 ticks
└── SessionStopped event