Initial commit: Ten31 Signal Engine (ingest, scoring brain, corpus seeds)

signal_engine/ingest/chunker.py

@@ -0,0 +1,36 @@
+"""Long-audio chunking (§4.1, §13.4).
+
+Podcasts run 1–3 h; the diarizer caps at 4 speakers/chunk and Spark 2 is a single GPU, so we cut
+long audio into ~2–3 min pieces sent SEQUENTIALLY (parallel audio → 503 FFT race). Each chunk is
+diarized independently and re-stitched across chunks by voiceprint (see speaker_stitch.py).
+Requires ffmpeg/ffprobe.
+"""
+from __future__ import annotations
+
+import subprocess
+from pathlib import Path
+
+CHUNK_SECONDS_DEFAULT = 150  # 2.5 min, within the ~2–3 min guidance
+
+
+def duration_seconds(src: str | Path) -> float:
+    out = subprocess.run(
+        ["ffprobe", "-v", "error", "-show_entries", "format=duration",
+         "-of", "default=noprint_wrappers=1:nokey=1", str(src)],
+        check=True, capture_output=True, text=True,
+    )
+    return float(out.stdout.strip())
+
+
+def chunk_audio(src: str | Path, out_dir: str | Path, *, chunk_seconds: int = CHUNK_SECONDS_DEFAULT) -> list[Path]:
+    """Split into fixed-length WAV chunks using ffmpeg's segment muxer (no re-encode of timing).
+    Returns chunk paths in order. Order matters: the queue sends them sequentially."""
+    out_dir = Path(out_dir)
+    out_dir.mkdir(parents=True, exist_ok=True)
+    pattern = str(out_dir / "chunk_%04d.wav")
+    subprocess.run(
+        ["ffmpeg", "-y", "-i", str(src), "-f", "segment", "-segment_time", str(chunk_seconds),
+         "-ar", "16000", "-ac", "1", "-reset_timestamps", "1", pattern],
+        check=True, capture_output=True,
+    )
+    return sorted(out_dir.glob("chunk_*.wav"))