Audio transcription support (#18398)

* install new packages for transcription support

* add config options

* audio maintainer modifications to support transcription

* pass main config to audio process

* embeddings support

* api and transcription post processor

* embeddings maintainer support for post processor

* live audio transcription with sherpa and faster-whisper

* update dispatcher with live transcription topic

* frontend websocket

* frontend live transcription

* frontend changes for speech events

* i18n changes

* docs

* mqtt docs

* fix linter

* use float16 and small model on gpu for real-time

* fix return value and use requestor to embed description instead of passing embeddings

* run real-time transcription in its own thread

* tweaks

* publish live transcriptions on their own topic instead of tracked_object_update

* config validator and docs

* clarify docs

frigate/embeddings/maintainer.py

@@ -37,6 +37,9 @@ from frigate.data_processing.common.license_plate.model import (
     LicensePlateModelRunner,
 )
 from frigate.data_processing.post.api import PostProcessorApi
+from frigate.data_processing.post.audio_transcription import (
+    AudioTranscriptionPostProcessor,
+)
 from frigate.data_processing.post.license_plate import (
     LicensePlatePostProcessor,
 )
@@ -176,6 +179,14 @@ class EmbeddingMaintainer(threading.Thread):
                 )
             )
 
+        if any(
+            c.enabled_in_config and c.audio_transcription.enabled
+            for c in self.config.cameras.values()
+        ):
+            self.post_processors.append(
+                AudioTranscriptionPostProcessor(self.config, self.requestor, metrics)
+            )
+
         self.stop_event = stop_event
         self.tracked_events: dict[str, list[Any]] = {}
         self.early_request_sent: dict[str, bool] = {}
@@ -372,6 +383,8 @@ class EmbeddingMaintainer(threading.Thread):
                             },
                             PostProcessDataEnum.recording,
                         )
+                elif isinstance(processor, AudioTranscriptionPostProcessor):
+                    continue
                 else:
                     processor.process_data(event_id, PostProcessDataEnum.event_id)