Catbot이 자기 이름을 못 알아듣던 이유 — 음성 인식 문법(Grammar) 버그를 잡다

"The cat" –sat (cost 4.1)-->
          –ate (cost 5.3)-->
          –sad (cost 9.8)-->

  SPOKEN: Catbot, engage.
    1. conf  114.1   kappa engage
    2. conf  112.1   cappa engage

 44  KOKORO_VOICES = ROOT / "models" / "voices-v1.0.bin"
 45  VOSK_BIG = ROOT / "models" / "vosk-model-en-us-0.22-lgraph"
 46  VOSK_SMALL = ROOT / "models" / "vosk-model-small-en-us-0.15"
 47 +# Dynamic-graph model — the only kind that accepts a runtime grammar. A model
 48 +# that ships a pre-composed graph/HCLG.fst has no seam to insert one into;
 49 +# Vosk logs "Runtime graphs are not supported by this model" and decodes
 50 +# freely, which is worse than having no grammar recognizer at all. Detected by
 51 +# the presence of graph/Gr.fst (the language model kept as a separate file).
 52 +VOSK_DYNAMIC = ROOT / "models" / "vosk-model-en-us-0.22-lgraph"
 53
 54  SAMPLE_RATE = 16000
 55  BASE = f"https://localhost:{os.getenv('CATBOT_PORT', '8800')}"

 105 +# ---- grammar-constrained wake/command recognizer ------------------------
 106 +# A SECOND recognizer decodes the same audio against nothing but the phrases
 107 +# below. It can't hear anything else, so "catbot engage" can't come out as
 108 +# "kappa engage" — that word doesn't exist in its graph. Anything Anna says
 109 +# that isn't a listed phrase decodes as "[unk]", which is exactly why this
 110 +# only ever SUPPLEMENTS the free recognizer (which still handles all
 111 +# conversation) instead of replacing it.
 117 +WAKE_NAME_FORMS = ["cat bot", "cat pot", "cat bought", "cat bottom", "cat but",
 118 +                   "catfight", "combat", "cabot", "kat bot", "cap pot"]
 119 +# what can follow his name (empty = just the name, which wakes him too)
 120 +GRAMMAR_TAILS = ["", "engage", "engaged", "wake up", "wake",
 121 +                 "are you listening", "are you there", "you there",
 122 +                 "go to sleep", "sleep", "stop", "stop listening",
 123 +                 "be quiet", "quiet", "shut up", "hush",
 124 +                 "open terminal", "close terminal", "approve", "skip"]
 125 +# phrases that stand alone, with or without his name
 126 +GRAMMAR_BARE = ["open terminal", "close terminal"]

 129 +def _build_grammar(model) -> str | None:
 130 +    """JSON phrase list for the constrained recognizer, filtered to words the
 131 +    model actually knows. Returns None if nothing usable survived."""
 132 +    names = list(WAKE_NAME_FORMS)
 133 +    # whatever wake_training.py learned from Anna's own mic counts too
 134 +    try:
 135 +        learned = json.loads((ROOT / "catbot_wake_variants.json").read_text())
 136 +        names += [w.strip().lower() for w in learned
 137 +                  if w.strip() and w.strip().lower() not in names]
 138 +    except Exception:
 139 +        pass
 140 +
 141 +    phrases = {f"{lead}{name} {tail}".strip()
 142 +               for lead in ("", "hey ")
 143 +               for name in names
 144 +               for tail in GRAMMAR_TAILS}
 145 +    phrases.update(GRAMMAR_BARE)

 474 +        # Second recognizer, constrained to the wake/command grammar above.
 475 +        # Runs on its own dynamic-graph model so the big model keeps handling
 476 +        # conversation with its full rescoring stack. Cost, measured: ~200 MB
 477 +        # of RAM and roughly DOUBLE the decode CPU (4.3 -> 8.0 ms per 62 ms
 478 +        # block) — the grammar shrinks the search, but a second acoustic model
 479 +        # still runs on every block. Still only 0.13x realtime, so it adds no
 480 +        # latency; set CATBOT_GRAMMAR=0 if that ever stops being true.
 481 +        self._grec = self._gmodel = None
 487 +                if not (gdir / "graph" / "Gr.fst").exists():
 488 +                    logger.warning(
 489 +                        f"grammar recognizer OFF: {gdir.name} has no dynamic "
 489 +                        f"graph (graph/Gr.fst) — runtime grammars need one")