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 == "" {

134
internal/config/config_test.go
View File

@@ -206,6 +206,102 @@ func TestWordRunReorderWindowRejectsInvalidEnvOverride(t *testing.T) {
}
}
func TestBackchannelMaxDurationDefaultsTo2(t *testing.T) {
t.Setenv(BackchannelMaxDurationEnv, "")
dir := t.TempDir()
input := writeTempFile(t, dir, "input.json")
output := filepath.Join(dir, "merged.json")
cfg, err := NewMergeConfig(MergeOptions{
InputFiles: []string{input},
OutputFile: output,
InputReader: DefaultInputReader,
OutputModules: DefaultOutputModules,
PreprocessingModules: DefaultPreprocessingModules,
PostprocessingModules: DefaultPostprocessingModules,
})
if err != nil {
t.Fatalf("config failed: %v", err)
}
if cfg.BackchannelMaxDuration != DefaultBackchannelMaxDuration {
t.Fatalf("backchannel max duration = %f, want %f", cfg.BackchannelMaxDuration, DefaultBackchannelMaxDuration)
}
}
func TestBackchannelMaxDurationUsesValidEnvOverride(t *testing.T) {
t.Setenv(BackchannelMaxDurationEnv, "1.5")
dir := t.TempDir()
input := writeTempFile(t, dir, "input.json")
output := filepath.Join(dir, "merged.json")
cfg, err := NewMergeConfig(MergeOptions{
InputFiles: []string{input},
OutputFile: output,
InputReader: DefaultInputReader,
OutputModules: DefaultOutputModules,
PreprocessingModules: DefaultPreprocessingModules,
PostprocessingModules: DefaultPostprocessingModules,
})
if err != nil {
t.Fatalf("config failed: %v", err)
}
if cfg.BackchannelMaxDuration != 1.5 {
t.Fatalf("backchannel max duration = %f, want 1.5", cfg.BackchannelMaxDuration)
}
}
func TestBackchannelMaxDurationRejectsInvalidEnvOverride(t *testing.T) {
assertPositiveFloatEnvValidation(t, BackchannelMaxDurationEnv)
}
func TestFillerMaxDurationDefaultsTo125(t *testing.T) {
t.Setenv(FillerMaxDurationEnv, "")
dir := t.TempDir()
input := writeTempFile(t, dir, "input.json")
output := filepath.Join(dir, "merged.json")
cfg, err := NewMergeConfig(MergeOptions{
InputFiles: []string{input},
OutputFile: output,
InputReader: DefaultInputReader,
OutputModules: DefaultOutputModules,
PreprocessingModules: DefaultPreprocessingModules,
PostprocessingModules: DefaultPostprocessingModules,
})
if err != nil {
t.Fatalf("config failed: %v", err)
}
if cfg.FillerMaxDuration != DefaultFillerMaxDuration {
t.Fatalf("filler max duration = %f, want %f", cfg.FillerMaxDuration, DefaultFillerMaxDuration)
}
}
func TestFillerMaxDurationUsesValidEnvOverride(t *testing.T) {
t.Setenv(FillerMaxDurationEnv, "1.75")
dir := t.TempDir()
input := writeTempFile(t, dir, "input.json")
output := filepath.Join(dir, "merged.json")
cfg, err := NewMergeConfig(MergeOptions{
InputFiles: []string{input},
OutputFile: output,
InputReader: DefaultInputReader,
OutputModules: DefaultOutputModules,
PreprocessingModules: DefaultPreprocessingModules,
PostprocessingModules: DefaultPostprocessingModules,
})
if err != nil {
t.Fatalf("config failed: %v", err)
}
if cfg.FillerMaxDuration != 1.75 {
t.Fatalf("filler max duration = %f, want 1.75", cfg.FillerMaxDuration)
}
}
func TestFillerMaxDurationRejectsInvalidEnvOverride(t *testing.T) {
assertPositiveFloatEnvValidation(t, FillerMaxDurationEnv)
}
func TestCoalesceGapDefaultsTo3(t *testing.T) {
dir := t.TempDir()
input := writeTempFile(t, dir, "input.json")
@@ -306,6 +402,44 @@ func TestCoalesceGapRejectsInvalidOverride(t *testing.T) {
}
}
func assertPositiveFloatEnvValidation(t *testing.T, envName string) {
t.Helper()
tests := []struct {
name string
value string
want string
}{
{name: "non-numeric", value: "fast", want: "must be a positive number"},
{name: "zero", value: "0", want: "must be positive"},
{name: "negative", value: "-0.1", want: "must be positive"},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
t.Setenv(envName, test.value)
dir := t.TempDir()
input := writeTempFile(t, dir, "input.json")
output := filepath.Join(dir, "merged.json")
_, err := NewMergeConfig(MergeOptions{
InputFiles: []string{input},
OutputFile: output,
InputReader: DefaultInputReader,
OutputModules: DefaultOutputModules,
PreprocessingModules: DefaultPreprocessingModules,
PostprocessingModules: DefaultPostprocessingModules,
})
if err == nil {
t.Fatal("expected error")
}
if !strings.Contains(err.Error(), test.want) {
t.Fatalf("expected error to contain %q, got %v", test.want, err)
}
})
}
}
func writeTempFile(t *testing.T, dir string, name string) string {
t.Helper()