Use physical CPU cores for Whisper runtime defaults

scripts/transcribe_meeting.py

@@ -0,0 +1,51 @@
+#!/usr/bin/env python3
+"""Transcribe one audio file with whisper.cpp; do not generate a protocol."""
+
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+if str(REPO_ROOT) not in sys.path:
+    sys.path.insert(0, str(REPO_ROOT))
+
+from src.meeting_lab.transcription.whisper import (  # noqa: E402
+    TranscriptionError,
+    transcribe_audio,
+)
+
+
+def parse_args(argv: list[str] | None = None) -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Create a compact Meeting Lab transcript with whisper.cpp.")
+    parser.add_argument("audio_file", type=Path)
+    parser.add_argument("--model", type=Path, required=True, help="Path to a whisper.cpp GGML model.")
+    parser.add_argument("--output-dir", type=Path, required=True)
+    parser.add_argument("--language", default="auto", help="Language code or 'auto' (default: auto).")
+    parser.add_argument("--threads", default="auto", help="Thread count or 'auto' for physical CPU cores (default: auto).")
+    parser.add_argument("--whisper-executable", default="whisper-cli", help="whisper.cpp CLI executable (default: whisper-cli).")
+    return parser.parse_args(argv)
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = parse_args(argv)
+    try:
+        result = transcribe_audio(
+            args.audio_file,
+            args.model,
+            args.output_dir,
+            args.language,
+            executable=args.whisper_executable,
+            threads=args.threads,
+        )
+    except TranscriptionError as exc:
+        print(f"Error: {exc}")
+        return 1
+    print(f"Transcript: {result.transcript_json}")
+    print(f"Runtime: {result.runtime_seconds:.3f} seconds")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())