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

Minor updates to overlap detection and segment coalescing logic

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-28 14:11:38 -05:00
parent 28c2eea340
commit a3ca6665a9
14 changed files with 662 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
internal/config/config.go
View File

@@ -11,16 +11,20 @@ import (
)
const (
DefaultInputReader = "json-files"
DefaultOutputModules = "json"
DefaultPreprocessingModules = "validate-raw,normalize-speakers,trim-text"
DefaultPostprocessingModules = "detect-overlaps,resolve-overlaps,backchannel,filler,coalesce,detect-overlaps,autocorrect,assign-ids,validate-output"
DefaultOverlapWordRunGap = 0.75
DefaultWordRunReorderWindow = 0.4
DefaultCoalesceGap = 3.0
DefaultCoalesceGapValue = "3.0"
OverlapWordRunGapEnv = "SERIATIM_OVERLAP_WORD_RUN_GAP"
WordRunReorderWindowEnv = "SERIATIM_OVERLAP_WORD_RUN_REORDER_WINDOW"
DefaultInputReader = "json-files"
DefaultOutputModules = "json"
DefaultPreprocessingModules = "validate-raw,normalize-speakers,trim-text"
DefaultPostprocessingModules = "detect-overlaps,resolve-overlaps,backchannel,filler,coalesce,detect-overlaps,autocorrect,assign-ids,validate-output"
DefaultOverlapWordRunGap = 0.75
DefaultWordRunReorderWindow = 0.4
DefaultCoalesceGap = 3.0
DefaultCoalesceGapValue = "3.0"
DefaultBackchannelMaxDuration = 2.0
DefaultFillerMaxDuration = 1.25
OverlapWordRunGapEnv = "SERIATIM_OVERLAP_WORD_RUN_GAP"
WordRunReorderWindowEnv = "SERIATIM_OVERLAP_WORD_RUN_REORDER_WINDOW"
BackchannelMaxDurationEnv = "SERIATIM_BACKCHANNEL_MAX_DURATION"
FillerMaxDurationEnv = "SERIATIM_FILLER_MAX_DURATION"
)
// MergeOptions captures raw CLI option values before validation.
@@ -39,30 +43,34 @@ type MergeOptions struct {
// Config is the validated runtime configuration for a merge invocation.
type Config struct {
InputFiles []string
OutputFile string
ReportFile string
SpeakersFile string
AutocorrectFile string
InputReader string
OutputModules []string
PreprocessingModules []string
PostprocessingModules []string
OverlapWordRunGap float64
WordRunReorderWindow float64
CoalesceGap float64
InputFiles []string
OutputFile string
ReportFile string
SpeakersFile string
AutocorrectFile string
InputReader string
OutputModules []string
PreprocessingModules []string
PostprocessingModules []string
OverlapWordRunGap float64
WordRunReorderWindow float64
CoalesceGap float64
BackchannelMaxDuration float64
FillerMaxDuration float64
}
// NewMergeConfig validates raw merge options and returns normalized config.
func NewMergeConfig(opts MergeOptions) (Config, error) {
cfg := Config{
InputReader: strings.TrimSpace(opts.InputReader),
OutputModules: nil,
PreprocessingModules: nil,
PostprocessingModules: nil,
OverlapWordRunGap: DefaultOverlapWordRunGap,
WordRunReorderWindow: DefaultWordRunReorderWindow,
CoalesceGap: DefaultCoalesceGap,
InputReader: strings.TrimSpace(opts.InputReader),
OutputModules: nil,
PreprocessingModules: nil,
PostprocessingModules: nil,
OverlapWordRunGap: DefaultOverlapWordRunGap,
WordRunReorderWindow: DefaultWordRunReorderWindow,
CoalesceGap: DefaultCoalesceGap,
BackchannelMaxDuration: DefaultBackchannelMaxDuration,
FillerMaxDuration: DefaultFillerMaxDuration,
}
if cfg.InputReader == "" {
@@ -136,6 +144,14 @@ func NewMergeConfig(opts MergeOptions) (Config, error) {
if err != nil {
return Config{}, err
}
cfg.BackchannelMaxDuration, err = parseBackchannelMaxDuration()
if err != nil {
return Config{}, err
}
cfg.FillerMaxDuration, err = parseFillerMaxDuration()
if err != nil {
return Config{}, err
}
return cfg, nil
}
@@ -222,6 +238,14 @@ func parseWordRunReorderWindow() (float64, error) {
return parsePositiveFloatEnv(WordRunReorderWindowEnv, DefaultWordRunReorderWindow)
}
func parseBackchannelMaxDuration() (float64, error) {
return parsePositiveFloatEnv(BackchannelMaxDurationEnv, DefaultBackchannelMaxDuration)
}
func parseFillerMaxDuration() (float64, error) {
return parsePositiveFloatEnv(FillerMaxDurationEnv, DefaultFillerMaxDuration)
}
func parseCoalesceGap(value string) (float64, error) {
value = strings.TrimSpace(value)
if value == "" {