Updated the normalize command to correct common errors in WhisperX-generated input transcripts
All checks were successful
ci/woodpecker/tag/release Pipeline was successful

This commit is contained in:
2026-05-16 23:05:42 -05:00
parent 6dbb7ab17e
commit b20438acf0
7 changed files with 357 additions and 66 deletions

View File

@@ -15,6 +15,7 @@ import (
// BuildResult contains normalize output plus deterministic transformation diagnostics.
type BuildResult struct {
Output any
OutputSegmentCount int
SortingChanged bool
IDsReassigned bool
SegmentsWithCategories int
@@ -35,6 +36,7 @@ func Build(parsed ParsedTranscript, cfg config.NormalizeConfig) (BuildResult, er
}
return BuildResult{
Output: output,
OutputSegmentCount: len(ordered),
SortingChanged: sortingChanged,
IDsReassigned: idsReassigned,
SegmentsWithCategories: segmentsWithCategories,
@@ -46,6 +48,7 @@ func Build(parsed ParsedTranscript, cfg config.NormalizeConfig) (BuildResult, er
}
return BuildResult{
Output: output,
OutputSegmentCount: len(ordered),
SortingChanged: sortingChanged,
IDsReassigned: idsReassigned,
SegmentsWithCategories: segmentsWithCategories,
@@ -57,6 +60,7 @@ func Build(parsed ParsedTranscript, cfg config.NormalizeConfig) (BuildResult, er
}
return BuildResult{
Output: output,
OutputSegmentCount: len(ordered),
SortingChanged: sortingChanged,
IDsReassigned: idsReassigned,
SegmentsWithCategories: segmentsWithCategories,