FIX: preset language=zh in whisperx load_model to prevent tokenizer race on long audio (32+ min)

- Bug: long audio (32+ min) batched inference hit NoneType 'sot_sequence' error
- Root cause: faster-whisper tokenizer reset to None between VAD chunks for multilingual inference when preset_language is None
- Fix: load model with language='zh' to set preset_language, avoiding tokenizer reset
- Side effect: slightly faster (no language detection per file)

Tested on F5 Tech Refresh meeting (32:46 audio, 80 segments, 8072 chars)
Previous: failed with AttributeError: 'NoneType' object has no attribute 'sot_sequence'
After: full transcript + summary generated successfully

transcribe_server.py

@@ -30,6 +30,7 @@ def get_model():
             "large-v3",
             "cpu",
             compute_type="int8",
+            language="zh",  # BUGFIX (2026-08-10): preset language → prevents tokenizer race condition crash on long audio (32+ min) where batched inference hits NoneType 'sot_sequence' bug
             asr_options={
                 "beam_size": 1,
                 "best_of": 1,