피파 목소리 위로 아빠 목소리 듣기

from collections import deque
from dataclasses import dataclass, field
from statistics import median


@dataclass
class BargeInDetector:
    """Dad talking over her, heard as loudness on the open, echo-cancelled mic."""
    calibrate: int = 5        # chunks that learn the floor: her echo + the room
    sustain: int = 3          # loud chunks in a row that count as Dad
    ratio: float = 3.5        # how far above the floor
    minimum: float = 700.0    # and never below this RMS
    seen: list = field(default_factory=list)
    floor: float | None = None
    loud: int = 0

    def reset(self) -> None:
        self.seen, self.floor, self.loud = [], None, 0

    def feed(self, level: float) -> bool:
        if self.floor is None:
            self.seen.append(level)
            if len(self.seen) >= self.calibrate:
                self.floor = median(self.seen)
            return False
        if level > max(self.floor * self.ratio, self.minimum):
            self.loud += 1
            return self.loud >= self.sustain
        self.loud = 0
        self.floor = self.floor * 0.9 + level * 0.1   # keep following the quiet
        return False


PREROLL_CHUNKS = 8            # about a second at 128 ms per chunk
preroll: deque = deque(maxlen=PREROLL_CHUNKS)
detector = BargeInDetector()

her_echo = [320, 410, 380, 350, 400, 900, 360, 390]     # one loud blip: a plosive
dad = [2400, 2800, 2600, 2500]
for t, level in enumerate(her_echo + dad):
    preroll.append((t, level))                          # the words that cut in, kept
    if detector.feed(level):
        print(f"cut in at chunk {t} ({t * 0.128:.2f}s): stop her, report heard, listen")
        print("  preroll sent to the transcriber first:", [c for c, _ in preroll])
        break
else:
    print("no cut-in")