Fix speaker diarization: WAV conversion, pyannote 4.0 compat, telemetry bug

- Convert non-WAV audio to 16kHz mono WAV before diarization (pyannote
  v4.0.4 AudioDecoder returns None duration for FLAC, causing crash)
- Handle pyannote 4.0 DiarizeOutput return type (unwrap .speaker_diarization)
- Disable pyannote telemetry (np.isfinite(None) bug with max_speakers)
- Use huggingface_hub.login() to persist token for all sub-downloads
- Pre-download sub-models (segmentation-3.0, speaker-diarization-community-1)
- Add third required model license link in settings UI
- Improve SpeakerManager hints based on settings state
- Add word-wrap to transcript text

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

python/voice_to_notes/ipc/handlers.py

@@ -90,15 +90,40 @@ def make_diarize_handler() -> HandlerFunc:
 
 def make_diarize_download_handler() -> HandlerFunc:
     """Create a handler that downloads/validates the diarization model."""
+    import os
 
     def handler(msg: IPCMessage) -> IPCMessage:
         payload = msg.payload
         hf_token = payload.get("hf_token")
 
         try:
+            import huggingface_hub
+
+            # Disable pyannote telemetry (has a bug in v4.0.4)
+            os.environ.setdefault("PYANNOTE_METRICS_ENABLED", "false")
             from pyannote.audio import Pipeline
 
-            print("[sidecar] Downloading diarization model...", file=sys.stderr, flush=True)
+            # Persist token globally so ALL huggingface_hub downloads use auth.
+            # Setting env var alone isn't enough — pyannote's internal sub-downloads
+            # (e.g. PLDA.from_pretrained) don't forward the token= parameter.
+            # login() writes the token to ~/.cache/huggingface/token which
+            # huggingface_hub reads automatically for all downloads.
+            if hf_token:
+                os.environ["HF_TOKEN"] = hf_token
+                huggingface_hub.login(token=hf_token, add_to_git_credential=False)
+
+            # Pre-download sub-models that pyannote loads internally.
+            # This ensures they're cached before Pipeline.from_pretrained
+            # tries to load them (where token forwarding can fail).
+            sub_models = [
+                "pyannote/segmentation-3.0",
+                "pyannote/speaker-diarization-community-1",
+            ]
+            for model_id in sub_models:
+                print(f"[sidecar] Pre-downloading {model_id}...", file=sys.stderr, flush=True)
+                huggingface_hub.snapshot_download(model_id, token=hf_token)
+
+            print("[sidecar] Downloading diarization pipeline...", file=sys.stderr, flush=True)
             pipeline = Pipeline.from_pretrained(
                 "pyannote/speaker-diarization-3.1",
                 token=hf_token,
@@ -111,26 +136,23 @@ def make_diarize_download_handler() -> HandlerFunc:
             )
         except Exception as e:
             error_msg = str(e)
+            print(f"[sidecar] Model download error: {error_msg}", file=sys.stderr, flush=True)
             # Make common errors more user-friendly
-            if "403" in error_msg and "gated" in error_msg.lower():
-                # Extract which model needs access
-                if "segmentation" in error_msg:
+            if "403" in error_msg or "gated" in error_msg.lower():
+                # Try to extract the specific model name from the error
+                import re
+                model_match = re.search(r"pyannote/[\w-]+", error_msg)
+                if model_match:
+                    model_name = model_match.group(0)
                     error_msg = (
-                        "Access denied for pyannote/segmentation-3.0. "
-                        "Please visit huggingface.co/pyannote/segmentation-3.0 "
-                        "and accept the license agreement."
-                    )
-                elif "speaker-diarization" in error_msg:
-                    error_msg = (
-                        "Access denied for pyannote/speaker-diarization-3.1. "
-                        "Please visit huggingface.co/pyannote/speaker-diarization-3.1 "
-                        "and accept the license agreement."
+                        f"Access denied for {model_name}. "
+                        f"Please visit huggingface.co/{model_name} "
+                        f"and accept the license agreement, then try again."
                     )
                 else:
                     error_msg = (
-                        "Access denied. Please accept the license agreements at: "
-                        "huggingface.co/pyannote/speaker-diarization-3.1 and "
-                        "huggingface.co/pyannote/segmentation-3.0"
+                        "Access denied. Please accept the license agreements for all "
+                        "required pyannote models on HuggingFace."
                     )
             elif "401" in error_msg:
                 error_msg = "Invalid token. Please check your HuggingFace token."