Add VibeVoice-ASR backend

Third ASR backend option alongside faster-whisper and qwen3. Builds
microsoft/VibeVoice from source (pinned to a specific commit, since it's
custom modeling code not in transformers' Auto* registry) into its own venv,
inheriting the base image's torch/CUDA. Comes with built-in speaker
diarization (VibeVoiceASRProcessor.post_process_transcription returns
per-segment speaker ids directly, no separate pyannote pass needed).

Verified end-to-end against a real recording: 200 OK, correct Korean
transcription, speaker labels populated.

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

app/ui/index.html

@@ -47,6 +47,7 @@
                     <select id="backend" name="backend">
                       <option value="faster-whisper" selected>faster-whisper</option>
                       <option value="qwen3">Qwen3-ASR</option>
+                      <option value="vibevoice">VibeVoice-ASR</option>
                     </select>
                   </label>
                   <label>모델