Merge pull request 'Pronunciation dictionary for piper' (#138) from task/458-pronunciation-dictionary-for-piper into master

piper reads a Russian sentence with a Russian voice, and a Latin service id
inside it comes out spelled, mangled or read as if it were a Russian word:
"Vikunja", "SearXNG", "homesrv". The lever available is the text, so the
dictionary maps a name to how it should be spelled for the voice to say it,
and mavttsd applies it at the last edge before piper — every caller's text
passes through that one point, and nothing upstream has to know how a name
sounds.

Data, not code. deploy/tts-lexicon.json ships 29 names; adding one needs a
restart of mavttsd and no rebuild of the daemon that produced the text. Off
unless -lexicon is set, like every other optional capability, and a path that
is set and unreadable stops startup — saying names wrong in silence is the
failure it exists to remove.

Two details worth keeping: the alternation is sorted longest-first, or "Home
Assistant" reads as "Хоум Assistant"; and the boundaries are written out
rather than left to \b, which is ASCII-only and never fires next to a
Cyrillic letter.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

cmd/mavttsd/main.go

@@ -23,6 +23,7 @@ import (
 	"syscall"
 
 	"github.com/kami/maven/internal/audio"
+	"github.com/kami/maven/internal/tts"
 	"github.com/kami/maven/internal/worker"
 )
 
@@ -39,15 +40,27 @@ func run(args []string) error {
 	model := flag.String("model", "", "path to piper onnx model file")
 	espeakData := flag.String("espeak_data", "", "path to espeak-ng data directory")
 	tashkeelModel := flag.String("tashkeel_model", "", "path to libtashkeel onnx model")
+	lexiconPath := flag.String("lexicon", "", "path to the pronunciation dictionary (json, name to spelling)")
 
 	flag.CommandLine.Parse(args)
 
 	ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM, syscall.SIGHUP)
 	defer stop()
 
+	// Read before the handler is built: a dictionary he asked for and that
+	// cannot be read is a startup failure, not a warning. Saying names wrong
+	// in silence is the thing it exists to stop.
+	lex, err := tts.LoadLexicon(*lexiconPath)
+	if err != nil {
+		return err
+	}
+	if lex.Size() > 0 {
+		log.Printf("mavttsd: pronunciation dictionary: %d names from %s", lex.Size(), *lexiconPath)
+	}
+
 	var s worker.Synthesizer
 	if *piperBin != "" && *model != "" {
-		s = newPiperHandler(*piperBin, *model, *espeakData, *tashkeelModel)
+		s = newPiperHandler(*piperBin, *model, *espeakData, *tashkeelModel, lex)
 		log.Printf("mavttsd: using piper tts (%s, model=%s)", *piperBin, *model)
 	} else {
 		log.Printf("mavttsd: no piper/model specified, using stub handler")

cmd/mavttsd/main_test.go

@@ -7,6 +7,7 @@ import (
 	"testing"
 
 	"github.com/kami/maven/internal/audio"
+	"github.com/kami/maven/internal/tts"
 	"github.com/kami/maven/internal/worker"
 )
 
@@ -117,3 +118,18 @@ func abs(n int) int {
 	}
 	return n
 }
+
+// The dictionary that ships in deploy/ must parse and must be non-empty. It is
+// data, so nothing else would catch a trailing comma before the voice did.
+func TestShippedLexiconLoads(t *testing.T) {
+	lex, err := tts.LoadLexicon(filepath.Join("..", "..", "deploy", "tts-lexicon.json"))
+	if err != nil {
+		t.Fatalf("deploy/tts-lexicon.json: %v", err)
+	}
+	if lex.Size() < 10 {
+		t.Errorf("shipped dictionary holds %d names, want the full list", lex.Size())
+	}
+	if got := lex.Apply("задача в Vikunja"); got == "задача в Vikunja" {
+		t.Error("the shipped dictionary did not rewrite a name it lists")
+	}
+}

cmd/mavttsd/piper_handler.go

@@ -9,6 +9,7 @@ import (
 	"os/exec"
 
 	"github.com/kami/maven/internal/audio"
+	"github.com/kami/maven/internal/tts"
 	"github.com/kami/maven/internal/worker"
 )
 
@@ -18,15 +19,20 @@ type piperHandler struct {
 	configPath    string
 	espeakData    string
 	tashkeelModel string
+	// lexicon rewrites service ids and Latin names into the spelling the
+	// Russian voice reads correctly (Vikunja #458). Nil-safe: an unconfigured
+	// dictionary rewrites nothing.
+	lexicon *tts.Lexicon
 }
 
-func newPiperHandler(piperPath, modelPath, espeakData, tashkeelModel string) *piperHandler {
+func newPiperHandler(piperPath, modelPath, espeakData, tashkeelModel string, lexicon *tts.Lexicon) *piperHandler {
 	return &piperHandler{
 		piperPath:     piperPath,
 		modelPath:     modelPath,
 		configPath:    modelPath + ".json",
 		espeakData:    espeakData,
 		tashkeelModel: tashkeelModel,
+		lexicon:       lexicon,
 	}
 }
 
@@ -66,7 +72,14 @@ func (h *piperHandler) Synthesize(ctx context.Context, req worker.SynthesizeReq)
 		return worker.SynthesizeResp{}, fmt.Errorf("piper: start: %w", err)
 	}
 
-	if _, err := io.WriteString(stdin, req.Text); err != nil {
+	// The dictionary is applied here, at the last edge before the voice: every
+	// caller's text passes through this one point, and nothing upstream has to
+	// know how a name is spelled out loud.
+	text := req.Text
+	if h.lexicon != nil {
+		text = h.lexicon.Apply(text)
+	}
+	if _, err := io.WriteString(stdin, text); err != nil {
 		stdin.Close()
 		stdout.Close()
 		_ = cmd.Wait()

deploy/tts-lexicon.json

@@ -0,0 +1,30 @@
+{
+  "Maven": "Мэйвен",
+  "Nexus": "Нексус",
+  "Praxis": "Праксис",
+  "Hexis": "Хексис",
+  "Vikunja": "Викунья",
+  "SearXNG": "сёрчиксэнджи",
+  "Kiwix": "Кивикс",
+  "Gitea": "Гитея",
+  "Home Assistant": "Хоум Ассистент",
+  "Docker": "Докер",
+  "Telegram": "Телеграм",
+  "ntfy": "энтифай",
+  "homesrv": "хоумсёрв",
+  "workpc": "воркписи",
+  "whisper": "виспер",
+  "piper": "пайпер",
+  "llama-server": "лама сервер",
+  "Qwen": "Квен",
+  "CalDAV": "калдав",
+  "IMAP": "аймап",
+  "API": "эй-пи-ай",
+  "CPU": "си-пи-ю",
+  "GPU": "джи-пи-ю",
+  "RAM": "оперативная память",
+  "SSD": "эс-эс-ди",
+  "uptime": "аптайм",
+  "backup": "бэкап",
+  "deploy": "деплой"
+}

docs/operations.md

@@ -90,6 +90,13 @@ export LD_LIBRARY_PATH="$ROOT/deps/piper"
 
 Without `-piper` it runs as a stub.
 
+`-lexicon deploy/tts-lexicon.json` adds the pronunciation dictionary: a flat
+JSON object of name to Russian spelling, applied to the text just before piper
+reads it. It is how `Vikunja` is said as a word rather than spelled out, and how
+`SearXNG` and `homesrv` are said at all. Off unless the flag is set; a path that
+is set and unreadable stops mavttsd rather than letting it say names wrong in
+silence. Adding a name needs a restart of mavttsd and nothing else.
+
 ## mavweb — PWA voice bridge (WebSocket ↔ TCP)
 
 No CGo, no deps; builds with stock Go.

internal/tts/lexicon.go

@@ -0,0 +1,128 @@
+package tts
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"regexp"
+	"sort"
+	"strings"
+)
+
+// Pronunciation dictionary (Vikunja #458).
+//
+// piper reads a Russian sentence with a Russian voice, and a Latin service id
+// inside that sentence comes out as letters or as noise: "Vikunja" is spelled
+// out, "SearXNG" is unreadable, and "homesrv" is read as if it were a word. The
+// fix is not a code change per name — it is a file of replacements applied to
+// the text before piper sees it.
+//
+// Spelling, not phonemes. piper has no lexicon input of its own here, so the
+// only lever is the text, and the entry for a name is how it should be spelled
+// in Russian for the voice to say it right. That also means a wrong entry is
+// visible: it is a word, and it is read out loud.
+//
+// The dictionary is data, so it ships as a file rather than a table in Go. A
+// name added to it needs no rebuild and no deploy of the daemon that owns the
+// text — only a restart of mavttsd, which is the process that reads it.
+
+// Lexicon rewrites names into the spelling the voice reads correctly.
+//
+// The zero value is usable and rewrites nothing, so a daemon with no dictionary
+// configured behaves exactly as it did before this existed.
+type Lexicon struct {
+	// Rules are held in one alternation rather than as a map, so a text is
+	// scanned once however many entries there are, and the longest name wins
+	// where two overlap ("Home Assistant" before "Home").
+	re *regexp.Regexp
+	// by lower-cased name, because the match is case-insensitive and the
+	// replacement is not derived from what was matched.
+	by map[string]string
+}
+
+// LoadLexicon reads a dictionary file: a flat JSON object of name to spelling.
+//
+//	{"Vikunja": "Викунья", "SearXNG": "сёрчиксэнджи"}
+//
+// An empty path returns an empty Lexicon and no error — the dictionary is off
+// unless configured, like every other optional capability. A path that is set
+// and unreadable IS an error: he asked for it, and silently saying names wrong
+// is the failure this exists to remove.
+func LoadLexicon(path string) (*Lexicon, error) {
+	if strings.TrimSpace(path) == "" {
+		return &Lexicon{}, nil
+	}
+	raw, err := os.ReadFile(path)
+	if err != nil {
+		return nil, fmt.Errorf("tts: lexicon %s: %w", path, err)
+	}
+	var entries map[string]string
+	if err := json.Unmarshal(raw, &entries); err != nil {
+		return nil, fmt.Errorf("tts: lexicon %s: %w", path, err)
+	}
+	return NewLexicon(entries), nil
+}
+
+// NewLexicon builds a lexicon from entries already in memory.
+func NewLexicon(entries map[string]string) *Lexicon {
+	names := make([]string, 0, len(entries))
+	by := make(map[string]string, len(entries))
+	for name, say := range entries {
+		name = strings.TrimSpace(name)
+		if name == "" || strings.TrimSpace(say) == "" {
+			continue
+		}
+		names = append(names, name)
+		by[strings.ToLower(name)] = say
+	}
+	if len(names) == 0 {
+		return &Lexicon{}
+	}
+	// Longest first: "Home Assistant" must match before "Home" does, and Go's
+	// regexp alternation is leftmost-first, not longest-match.
+	sort.Slice(names, func(i, j int) bool { return len(names[i]) > len(names[j]) })
+	quoted := make([]string, len(names))
+	for i, n := range names {
+		quoted[i] = regexp.QuoteMeta(n)
+	}
+	// The boundaries are written out rather than left to \b, which is ASCII-only
+	// and never fires next to a Cyrillic letter — so "в Vikunja," would not
+	// match with \b on the left in a Russian sentence.
+	pattern := `(?i)(^|[^\p{L}\p{N}_])(` + strings.Join(quoted, "|") + `)($|[^\p{L}\p{N}_])`
+	return &Lexicon{re: regexp.MustCompile(pattern), by: by}
+}
+
+// Apply rewrites every name in the text. Text with no name in it comes back
+// unchanged and untouched.
+func (l *Lexicon) Apply(text string) string {
+	if l == nil || l.re == nil || text == "" {
+		return text
+	}
+	// Twice, because two names separated by a single space share the character
+	// between them and one pass consumes it: "Nexus Praxis" would leave the
+	// second name alone otherwise.
+	out := l.replaceOnce(text)
+	return l.replaceOnce(out)
+}
+
+func (l *Lexicon) replaceOnce(text string) string {
+	return l.re.ReplaceAllStringFunc(text, func(m string) string {
+		groups := l.re.FindStringSubmatch(m)
+		if groups == nil {
+			return m
+		}
+		say, ok := l.by[strings.ToLower(groups[2])]
+		if !ok {
+			return m
+		}
+		return groups[1] + say + groups[3]
+	})
+}
+
+// Size reports how many names are loaded, for the startup log line.
+func (l *Lexicon) Size() int {
+	if l == nil {
+		return 0
+	}
+	return len(l.by)
+}

internal/tts/lexicon_test.go

@@ -0,0 +1,85 @@
+package tts
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestLexiconRewritesNames(t *testing.T) {
+	lex := NewLexicon(map[string]string{
+		"Vikunja":        "Викунья",
+		"Home Assistant": "Хоум Ассистент",
+		"Home":           "Хоум",
+		"GPU":            "джи-пи-ю",
+	})
+	for _, tc := range []struct{ in, want string }{
+		{"задача в Vikunja готова", "задача в Викунья готова"},
+		// Case-insensitive: the router and the model both change the case of a
+		// name on the way through.
+		{"открой vikunja.", "открой Викунья."},
+		// Longest first, or "Home Assistant" is read as "Хоум Assistant".
+		{"Home Assistant не отвечает", "Хоум Ассистент не отвечает"},
+		// Two names in a row share the space between them, which one pass
+		// would consume.
+		{"GPU GPU", "джи-пи-ю джи-пи-ю"},
+		// Not a word boundary: a name inside a longer token is left alone.
+		{"vikunjaless", "vikunjaless"},
+		{"ничего не совпало", "ничего не совпало"},
+		{"", ""},
+	} {
+		if got := lex.Apply(tc.in); got != tc.want {
+			t.Errorf("Apply(%q) = %q, want %q", tc.in, got, tc.want)
+		}
+	}
+}
+
+// The zero value and an unconfigured path rewrite nothing, so a daemon with no
+// dictionary behaves as it did before this existed.
+func TestLexiconOffByDefault(t *testing.T) {
+	var zero *Lexicon
+	if got := zero.Apply("Vikunja"); got != "Vikunja" {
+		t.Errorf("nil lexicon rewrote %q", got)
+	}
+	lex, err := LoadLexicon("")
+	if err != nil {
+		t.Fatalf("LoadLexicon(\"\"): %v", err)
+	}
+	if lex.Size() != 0 || lex.Apply("Vikunja") != "Vikunja" {
+		t.Errorf("empty path produced a live lexicon of %d names", lex.Size())
+	}
+}
+
+// A path he set and that cannot be read is a startup failure. Saying names
+// wrong in silence is what the dictionary exists to stop.
+func TestLexiconLoadErrors(t *testing.T) {
+	if _, err := LoadLexicon(filepath.Join(t.TempDir(), "nope.json")); err == nil {
+		t.Error("a missing dictionary must be an error")
+	}
+	bad := filepath.Join(t.TempDir(), "bad.json")
+	if err := os.WriteFile(bad, []byte("{not json"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := LoadLexicon(bad); err == nil {
+		t.Error("an unparseable dictionary must be an error")
+	}
+}
+
+func TestLexiconRoundTripsAFile(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "lex.json")
+	if err := os.WriteFile(path, []byte(`{"Praxis":"Праксис","  ":"skipped","Nexus":""}`), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	lex, err := LoadLexicon(path)
+	if err != nil {
+		t.Fatalf("LoadLexicon: %v", err)
+	}
+	// Blank names and blank spellings are dropped: an entry that says nothing
+	// would delete the word it matched.
+	if lex.Size() != 1 {
+		t.Fatalf("Size = %d, want 1", lex.Size())
+	}
+	if got := lex.Apply("Praxis молчит"); got != "Праксис молчит" {
+		t.Errorf("Apply = %q", got)
+	}
+}