Fix audio transcription (#20395)

* camera level config

* set up model runner on thread start to avoid unpickling error

* ensure feature is enabled globally

* suppress info logs from faster_whisper

* fix incorrect event_type for api and audio timeline entries

* docs

* fix

* clean up

frigate/data_processing/real_time/whisper_online.py

@@ -141,6 +141,8 @@ class FasterWhisperASR(ASRBase):
     def transcribe(self, audio, init_prompt=""):
         from faster_whisper import BatchedInferencePipeline
 
+        logging.getLogger("faster_whisper").setLevel(logging.WARNING)
+
         # tested: beam_size=5 is faster and better than 1 (on one 200 second document from En ESIC, min chunk 0.01)
         batched_model = BatchedInferencePipeline(model=self.model)
         segments, info = batched_model.transcribe(