eric/seriatim
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 4 Wiki Activity

Implemented a module to detect filler segments, and skip them for purposes of same-speaker segment coalescing

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-27 19:58:55 -05:00
parent bbfb8aba44
commit fb0519c561
9 changed files with 319 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
internal/config/config.go
View File

@@ -14,7 +14,7 @@ const (
DefaultInputReader = "json-files"
DefaultOutputModules = "json"
DefaultPreprocessingModules = "validate-raw,normalize-speakers,trim-text"
DefaultPostprocessingModules = "detect-overlaps,resolve-overlaps,backchannel,coalesce,detect-overlaps,autocorrect,assign-ids,validate-output"
DefaultPostprocessingModules = "detect-overlaps,resolve-overlaps,backchannel,filler,coalesce,detect-overlaps,autocorrect,assign-ids,validate-output"
DefaultOverlapWordRunGap = 0.75
DefaultWordRunReorderWindow = 0.4
DefaultCoalesceGap = 3.0