mavttsd: a pronunciation dictionary, so she says the names right (V-458)
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>
This commit is contained in:
+14
-1
@@ -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")
|
||||
|
||||
Reference in New Issue
Block a user