Skip to content

Make transcript cleanup conservative and measurable #16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
none23 merged 18 commits into from
Sep 2, 2026
Merged

Make transcript cleanup conservative and measurable #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
ec164ca
test: add transcript cleanup eval corpus
none23 Sep 2, 2026
6e38082
refactor: make model cleanup authoritative
none23 Sep 2, 2026
579335a
test: align unfinished fragment expectation
none23 Sep 2, 2026
79d8988
feat: make transcript cleanup conservative
none23 Sep 2, 2026
fb77df5
test: apply transcript eval review feedback
none23 Sep 2, 2026
e07a723
test: support transcript prompt comparisons
none23 Sep 2, 2026
d9c20e7
test: record transcript cleanup eval results
none23 Sep 2, 2026
dc9c1ec
test: run transcript eval through Codex
none23 Sep 2, 2026
33a9d26
test: isolate recognition from hyphenation
none23 Sep 2, 2026
b655d50
feat: improve transcript recognition cleanup
none23 Sep 2, 2026
ae89a5b
test: record initial Codex transcript eval
none23 Sep 2, 2026
dadaea4
test: keep version suffix capitalization out of scope
none23 Sep 2, 2026
019da9b
feat: cover recurring transcript recognition errors
none23 Sep 2, 2026
2e30f66
test: score cleanup intent separately from style
none23 Sep 2, 2026
46bfd4c
feat: normalize spoken measurements
none23 Sep 2, 2026
2c3c2d9
test: record optimized Codex transcript eval
none23 Sep 2, 2026
3d0a240
chore: remove transcript eval results
none23 Sep 2, 2026
155068a
refactor: keep transcript eval subscription-only
none23 Sep 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .github/workflows/ci.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,5 +91,5 @@ jobs:

- name: Check shell scripts
run: |
shellcheck install.sh integrations/sway/local-wisper.sh scripts/baml
bash -n install.sh integrations/sway/local-wisper.sh scripts/baml
shellcheck install.sh integrations/sway/local-wisper.sh scripts/baml scripts/run-cleanup-eval-codex
bash -n install.sh integrations/sway/local-wisper.sh scripts/baml scripts/run-cleanup-eval-codex
4 changes: 2 additions & 2 deletions baml_src/app.baml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -360,13 +360,13 @@ test "history receives the raw and final transcript" {
assert.equal(saved, ["raw words|Final words.|Model|gpt-5.6-luna"])
}

test "local processing records the raw and final transcript" {
test "local processing preserves the transcript" {
let transcript = prepare_transcript("version zero point one.", parse_options([]));
assert.equal(
transcript,
TranscriptRecord {
raw_text: "version zero point one.",
final_text: "version 0.1",
final_text: "version zero point one.",
processing: TranscriptProcessing.Local,
post_process_model: null,
},
Expand Down
Loading