"""
Manual integration test for speaker diarization via pyannote.

Requires:
  - HF_TOKEN env var (or set below)
  - CF_VOICE_DIARIZE=1
  - ffmpeg on PATH
  - A local audio/video file (edit MEDIA_FILE below)
  - pip install cf-voice[inference]

Run:
  HF_TOKEN=hf_... CF_VOICE_DIARIZE=1 python scripts/test_diarize_real.py
"""
from __future__ import annotations

import asyncio
import os
import subprocess

import numpy as np

# Override if not in env
if not os.environ.get("HF_TOKEN"):
    raise SystemExit("Set HF_TOKEN in env before running this script.")
os.environ.setdefault("CF_VOICE_DIARIZE", "1")

MEDIA_FILE = "/Library/Series/Hogan's Heroes/Season 3/Hogan's Heroes - S03E19 - Hogan, Go Home.mkv"
START_S = 120
DURATION_S = 2
SAMPLE_RATE = 16_000

from cf_voice.diarize import Diarizer, SpeakerTracker  # noqa: E402


async def main() -> None:
    d = Diarizer.from_env()
    tracker = SpeakerTracker()

    proc = subprocess.run(
        [
            "ffmpeg", "-i", MEDIA_FILE,
            "-ss", str(START_S),
            "-t", str(DURATION_S),
            "-ar", str(SAMPLE_RATE),
            "-ac", "1",
            "-f", "s16le",
            "-",
        ],
        capture_output=True,
        check=True,
    )
    audio = np.frombuffer(proc.stdout, dtype=np.int16).astype(np.float32) / 32768.0
    rms = float(np.sqrt(np.mean(audio**2)))
    print(f"audio: {len(audio)} samples, {len(audio) / SAMPLE_RATE:.2f}s, rms={rms:.4f}")

    segs = await d.diarize_async(audio)
    print(f"segments ({len(segs)}): {segs}")

    mid = len(audio) / 2.0 / SAMPLE_RATE
    label = d.speaker_at(segs, mid, tracker)
    print(f"speaker_at({mid:.2f}s): {label}")


if __name__ == "__main__":
    asyncio.run(main())