Simplify the CLI interface and update documentation accordingly

README.md

@@ -2,7 +2,7 @@
 
 `seriatim` merges per-speaker WhisperX-style JSON transcripts into a single JSON transcript that preserves speaker identity and chronological order.
 
-The current implementation supports the `merge` command. It reads one or more input JSON files, maps each input file to a canonical speaker using `speakers.yml`, sorts all segments by timestamp, assigns consecutive numeric `id` values, and writes a merged JSON artifact.
+The current implementation supports the `merge` command. It reads one or more input JSON files, optionally maps each input file to a canonical speaker using `speakers.yml`, sorts all segments by timestamp, assigns consecutive numeric `id` values, and writes a merged JSON artifact.
 
 ## Usage
 
@@ -12,7 +12,6 @@ Run from source:
 go run ./cmd/seriatim merge \
   --input-file samples/raw/2026-04-19-Eric_Rakestraw.json \
   --input-file samples/raw/2026-04-19-Mike_Brown.json \
-  --speakers samples/speakers.yml \
   --output-file merged.json
 ```
 
@@ -22,7 +21,6 @@ Optional report output:
 go run ./cmd/seriatim merge \
   --input-file eric.json \
   --input-file mike.json \
-  --speakers speakers.yml \
   --output-file merged.json \
   --report-file report.json
 ```
@@ -36,17 +34,17 @@ seriatim merge [flags]
 Required flags for the default pipeline:
 
 - `--input-file`: input transcript JSON file. Repeat once per speaker/input file.
-- `--speakers`: speaker map YAML file. Required because `normalize-speakers` is enabled by default.
 - `--output-file`: merged transcript JSON output path.
 
 Optional flags:
 
 - `--report-file`: write a JSON report with pipeline events.
+- `--speakers`: speaker map YAML file. When omitted, input file basenames are used as speaker labels.
+- `--autocorrect`: autocorrect rules file. When omitted, the default `autocorrect` module no-ops.
 - `--input-reader`: input reader module. Default: `json-files`.
 - `--output-modules`: comma-separated output modules. Default: `json`.
 - `--preprocessing-modules`: comma-separated preprocessing modules. Default: `validate-raw,normalize-speakers,trim-text`.
-- `--postprocessing-modules`: comma-separated postprocessing modules. Default: `detect-overlaps,resolve-overlaps,assign-ids,validate-output`.
+- `--postprocessing-modules`: comma-separated postprocessing modules. Default: `detect-overlaps,resolve-overlaps,autocorrect,assign-ids,validate-output`.
-- `--autocorrect`: autocorrect rules file. Required when the postprocessing `autocorrect` module is enabled.
 
 ## Input JSON Format
 
@@ -76,6 +74,8 @@ Other WhisperX fields, including `words` and raw diarization speaker labels, are
 
 `speakers.yml` maps input files to canonical speaker names using ordered substring rules:
 
+This file is optional. If `--speakers` is omitted, `seriatim` uses each input file basename as the segment speaker label.
+
 ```yaml
 match:
   - speaker: "Eric Rakestraw"
@@ -137,7 +137,7 @@ The merged output uses the current seriatim envelope:
     "input_reader": "json-files",
     "input_files": ["eric.json", "mike.json"],
     "preprocessing_modules": ["validate-raw", "normalize-speakers", "trim-text"],
-    "postprocessing_modules": ["detect-overlaps", "resolve-overlaps", "assign-ids", "validate-output"],
+    "postprocessing_modules": ["detect-overlaps", "resolve-overlaps", "autocorrect", "assign-ids", "validate-output"],
     "output_modules": ["json"]
   },
   "segments": [
@@ -165,16 +165,14 @@ Final segment IDs are assigned after sorting and start at `1`.
 
 ## Autocorrect
 
-Autocorrect is an opt-in postprocessing module. It is not part of the default pipeline.
+Autocorrect is included in the default postprocessing pipeline. If `--autocorrect` is omitted, the module leaves transcript text unchanged and records a skip event in the optional report.
 
-Enable it by adding `autocorrect` to `--postprocessing-modules` and passing `--autocorrect`:
+Enable corrections by passing `--autocorrect`:
 
 ```sh
 go run ./cmd/seriatim merge \
   --input-file input.json \
-  --speakers speakers.yml \
   --autocorrect autocorrect.yml \
-  --postprocessing-modules detect-overlaps,resolve-overlaps,autocorrect,assign-ids,validate-output \
   --output-file merged.json
 ```
 

internal/builtin/postprocess.go

@@ -58,6 +58,11 @@ func (autocorrectPostprocessor) Process(ctx context.Context, in model.MergedTran
 	if err := ctx.Err(); err != nil {
 		return model.MergedTranscript{}, nil, err
 	}
+	if cfg.AutocorrectFile == "" {
+		return in, []report.Event{
+			report.Info("postprocessing", "autocorrect", "skipped autocorrect because no autocorrect file was supplied"),
+		}, nil
+	}
 
 	rules, err := autocorrect.Load(cfg.AutocorrectFile)
 	if err != nil {

internal/builtin/preprocess.go

@@ -3,6 +3,7 @@ package builtin
 import (
 	"context"
 	"fmt"
+	"path/filepath"
 	"strings"
 
 	"gitea.maximumdirect.net/eric/seriatim/internal/config"
@@ -99,17 +100,26 @@ func (normalizeSpeakers) Process(ctx context.Context, in pipeline.PreprocessStat
 		return pipeline.PreprocessState{}, nil, fmt.Errorf("preprocessing module %q requires state %q but received %q", "normalize-speakers", pipeline.StateRaw, in.State)
 	}
 
-	speakers, err := speaker.LoadMap(cfg.SpeakersFile)
+	var speakers speaker.Map
+	useSpeakerMap := cfg.SpeakersFile != ""
+	if useSpeakerMap {
+		var err error
+		speakers, err = speaker.LoadMap(cfg.SpeakersFile)
 		if err != nil {
 			return pipeline.PreprocessState{}, nil, err
 		}
+	}
 
 	canonical := make([]model.CanonicalTranscript, 0, len(in.Raw))
 	for _, raw := range in.Raw {
-		canonicalSpeaker, err := speakers.SpeakerForSource(raw.Source)
+		canonicalSpeaker := filepath.Base(raw.Source)
+		if useSpeakerMap {
+			var err error
+			canonicalSpeaker, err = speakers.SpeakerForSource(raw.Source)
 			if err != nil {
 				return pipeline.PreprocessState{}, nil, err
 			}
+		}
 
 		segments := make([]model.Segment, 0, len(raw.Segments))
 		for index, rawSegment := range raw.Segments {
@@ -129,11 +139,16 @@ func (normalizeSpeakers) Process(ctx context.Context, in pipeline.PreprocessStat
 		})
 	}
 
+	message := "created canonical transcript(s) from raw input"
+	if !useSpeakerMap {
+		message = "created canonical transcript(s) using input basenames as speaker labels"
+	}
+
 	return pipeline.PreprocessState{
 			State:     pipeline.StateCanonical,
 			Raw:       append([]model.RawTranscript(nil), in.Raw...),
 			Canonical: canonical,
 		}, []report.Event{
-			report.Info("preprocessing", "normalize-speakers", "created canonical transcript(s) from raw input"),
+			report.Info("preprocessing", "normalize-speakers", message),
 		}, nil
 }

internal/cli/merge_test.go

@@ -90,6 +90,7 @@ func TestMergeWritesMergedOutputAndReport(t *testing.T) {
 		"placeholder-merger",
 		"detect-overlaps",
 		"resolve-overlaps",
+		"autocorrect",
 		"assign-ids",
 		"validate-output",
 		"json",
@@ -274,43 +275,37 @@ func TestMissingInputFileFailsBeforePipelineExecution(t *testing.T) {
 	}
 }
 
-func TestNormalizeSpeakersRequiresSpeakersFile(t *testing.T) {
+func TestDefaultMergeWorksWithoutSpeakersOrAutocorrect(t *testing.T) {
 	dir := t.TempDir()
-	input := writeJSONFile(t, dir, "input.json", `{"segments":[]}`)
+	input := writeJSONFile(t, dir, "input.json", `{"segments":[{"start":1,"end":2,"text":"Frank"}]}`)
 	output := filepath.Join(dir, "merged.json")
+	reportPath := filepath.Join(dir, "report.json")
 
 	err := executeMerge(
 		"--input-file", input,
 		"--output-file", output,
+		"--report-file", reportPath,
 	)
-	if err == nil {
+	if err != nil {
-		t.Fatal("expected error")
+		t.Fatalf("merge failed: %v", err)
 	}
-	if !strings.Contains(err.Error(), "--speakers is required") {
-		t.Fatalf("unexpected error: %v", err)
-	}
-}
 
-func TestAutocorrectRequiresAutocorrectFile(t *testing.T) {
+	var transcript model.FinalTranscript
-	dir := t.TempDir()
+	readJSON(t, output, &transcript)
-	input := writeJSONFile(t, dir, "input.json", `{"segments":[]}`)
+	if got, want := transcript.Segments[0].Speaker, "input.json"; got != want {
-	speakers := writeYAMLFile(t, dir, "speakers.yml", `match:
+		t.Fatalf("speaker = %q, want %q", got, want)
-  - speaker: Alice
-    match: ["input.json"]
-`)
-	output := filepath.Join(dir, "merged.json")
-
-	err := executeMerge(
-		"--input-file", input,
-		"--speakers", speakers,
-		"--output-file", output,
-		"--postprocessing-modules", "detect-overlaps,resolve-overlaps,autocorrect,assign-ids,validate-output",
-	)
-	if err == nil {
-		t.Fatal("expected error")
 	}
-	if !strings.Contains(err.Error(), "--autocorrect is required") {
+	if got, want := transcript.Segments[0].Text, "Frank"; got != want {
-		t.Fatalf("unexpected error: %v", err)
+		t.Fatalf("text = %q, want %q", got, want)
+	}
+
+	var rpt report.Report
+	readJSON(t, reportPath, &rpt)
+	if !hasReportEvent(rpt, "preprocessing", "normalize-speakers", "using input basenames") {
+		t.Fatal("expected normalize-speakers fallback report event")
+	}
+	if !hasReportEvent(rpt, "postprocessing", "autocorrect", "skipped autocorrect") {
+		t.Fatal("expected autocorrect skip report event")
 	}
 }
 
@@ -402,6 +397,28 @@ func TestPostprocessingAutocorrectUpdatesOutputAndReport(t *testing.T) {
 	}
 }
 
+func TestInvalidAutocorrectFileFailsWhenProvided(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{"segments":[{"start":1,"end":2,"text":"Frank"}]}`)
+	output := filepath.Join(dir, "merged.json")
+	autocorrect := writeYAMLFile(t, dir, "autocorrect.yml", `autocorrect:
+  - target: ""
+    match: ["Frank"]
+`)
+
+	err := executeMerge(
+		"--input-file", input,
+		"--autocorrect", autocorrect,
+		"--output-file", output,
+	)
+	if err == nil {
+		t.Fatal("expected error")
+	}
+	if !strings.Contains(err.Error(), "must include target") {
+		t.Fatalf("unexpected error: %v", err)
+	}
+}
+
 func TestOutputJSONIsByteStable(t *testing.T) {
 	dir := t.TempDir()
 	inputA := writeJSONFile(t, dir, "a.json", `{"segments":[{"start":2,"end":3,"text":"a"}]}`)
@@ -658,6 +675,15 @@ func equalStrings(left []string, right []string) bool {
 	return true
 }
 
+func hasReportEvent(rpt report.Report, stage string, module string, messageSubstring string) bool {
+	for _, event := range rpt.Events {
+		if event.Stage == stage && event.Module == module && strings.Contains(event.Message, messageSubstring) {
+			return true
+		}
+	}
+	return false
+}
+
 func assertSegment(t *testing.T, segment model.Segment, id int, source string, sourceIndex int, speaker string, start float64, end float64, text string) {
 	t.Helper()
 

internal/config/config.go

@@ -13,7 +13,7 @@ const (
 	DefaultInputReader           = "json-files"
 	DefaultOutputModules         = "json"
 	DefaultPreprocessingModules  = "validate-raw,normalize-speakers,trim-text"
-	DefaultPostprocessingModules = "detect-overlaps,resolve-overlaps,assign-ids,validate-output"
+	DefaultPostprocessingModules = "detect-overlaps,resolve-overlaps,autocorrect,assign-ids,validate-output"
 )
 
 // MergeOptions captures raw CLI option values before validation.
@@ -98,27 +98,13 @@ func NewMergeConfig(opts MergeOptions) (Config, error) {
 		cfg.AutocorrectFile = ""
 	}
 
-	if contains(cfg.PreprocessingModules, "normalize-speakers") {
+	if cfg.SpeakersFile != "" {
-		if cfg.SpeakersFile == "" {
-			return Config{}, errors.New("--speakers is required when normalize-speakers is enabled")
-		}
-		if err := requireFile(cfg.SpeakersFile, "--speakers"); err != nil {
-			return Config{}, err
-		}
-	} else if cfg.SpeakersFile != "" {
 		if err := requireFile(cfg.SpeakersFile, "--speakers"); err != nil {
 			return Config{}, err
 		}
 	}
 
-	if contains(cfg.PostprocessingModules, "autocorrect") {
+	if cfg.AutocorrectFile != "" {
-		if cfg.AutocorrectFile == "" {
-			return Config{}, errors.New("--autocorrect is required when autocorrect is enabled")
-		}
-		if err := requireFile(cfg.AutocorrectFile, "--autocorrect"); err != nil {
-			return Config{}, err
-		}
-	} else if cfg.AutocorrectFile != "" {
 		if err := requireFile(cfg.AutocorrectFile, "--autocorrect"); err != nil {
 			return Config{}, err
 		}