feat: DelaySum beamform plus hop process latency

Keep C920 stereo through SpeechBrain GCC-PHAT Delay-and-Sum, then
MetricGAN, and publish mono to LiveKit. Record last_dt_ms and log
process_ms/capture_ms every 50 hops for the latency plan.

run_worker.py

@@ -37,6 +37,7 @@ def main() -> int:
                     default="speechbrain/metricgan-plus-voicebank")
     ap.add_argument("--enhance-chunk-s", type=float, default=1.0)
     ap.add_argument("--enhance-hop-s", type=float, default=0.2)
+    ap.add_argument("--beamform-mode", default="auto")
     args = ap.parse_args()
 
     cam = json.loads(args.camera_json)
@@ -60,6 +61,7 @@ def main() -> int:
             sample_rate=args.audio_rate,
             chunk_s=args.enhance_chunk_s,
             hop_s=args.enhance_hop_s,
+            beamform=args.beamform_mode,
         )
         log.info("audio backend: %s", cleaner.backend)
 
@@ -138,6 +140,7 @@ def main() -> int:
                 # chunk * 2 ch * 2 bytes
                 need = chunk * 2 * 2
                 buf = b""
+                hops = 0
                 while aproc.poll() is None:
                     data = await loop.run_in_executor(
                         None, aproc.stdout.read, 4096)
@@ -146,21 +149,28 @@ def main() -> int:
                     buf += data
                     while len(buf) >= need:
                         piece, buf = buf[:need], buf[need:]
-                        pcm_stereo = np.frombuffer(piece, dtype=np.int16)
-                        pcm_mono = pcm_stereo.reshape(-1, 2).mean(
-                            axis=1).astype(np.int16)
-                        # align to full chunks
-                        usable = (len(pcm_mono) // chunk) * chunk
+                        pcm_stereo = np.frombuffer(
+                            piece, dtype=np.int16).reshape(-1, 2)
+                        n_frames = pcm_stereo.shape[0]
+                        usable = (n_frames // chunk) * chunk
                         if usable:
                             cleaned = await loop.run_in_executor(
                                 None, cleaner.process,
-                                pcm_mono[:usable])
+                                pcm_stereo[:usable])
+                            t_cap = time.perf_counter()
                             await audio_source.capture_frame(
                                 rtc.AudioFrame(
                                     cleaned.tobytes(),
                                     args.audio_rate,
                                     1,
                                     len(cleaned)))
+                            hops += 1
+                            if hops % 50 == 0:
+                                log.info(
+                                    "audio hop process_ms=%.1f capture_ms=%.1f",
+                                    cleaner.last_dt_ms,
+                                    (time.perf_counter() - t_cap) * 1000.0,
+                                )
 
             aproc = subprocess.Popen(
                 ["ffmpeg", "-hide_banner", "-loglevel", "error",