Fix broken file transcription and speaker diarization

qwen3 backend: model list pointed at nonexistent HF repos (Qwen3-ASR-2B/8B
don't exist), and inference went through the generic HF ASR pipeline with
Whisper-only options (return_timestamps, task/language generate_kwargs) that
Qwen3-ASR's chat-style architecture doesn't support. Switched to the real
0.6B/1.7B-hf checkpoints and drive them via
processor.apply_transcription_request() + model.generate(). Also added an
ffmpeg pre-conversion step since the model's feature extractor can't decode
m4a via librosa.

faster-whisper backend: speaker diarization was broken by two pyannote.audio
API changes it hadn't caught up with (use_auth_token= renamed to token=, and
pipeline() now returns a DiarizeOutput wrapper instead of an Annotation
directly). Also pinned LD_LIBRARY_PATH for that worker so it picks up its own
venv's cuDNN instead of the older one shadowing it via the container's global
LD_LIBRARY_PATH, which crashed pyannote's GPU init.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

app/asr/router.py

@@ -48,7 +48,7 @@ def config() -> Dict[str, Any]:
                 "models": ["tiny", "base", "small", "medium", "large-v3", "large-v2", "turbo"],
             },
             "qwen3": {
-                "models": ["Qwen/Qwen3-ASR-2B", "Qwen/Qwen3-ASR-8B"],
+                "models": ["Qwen/Qwen3-ASR-0.6B-hf", "Qwen/Qwen3-ASR-1.7B-hf"],
             },
         },
     }