Miscellaneous Fixes (#21102)

* ensure audio events display timeline entries in tracking details

* tweak tracking details layout for small desktop sizes

* update transcription docs

* Update classification docs for training recommendations

* Make number of classification images to be kept configurable

* Add bird to classification reference

* Fix incorrect averaging of the segments so it correctly only uses the most recent segments

* fix trigger logic

* add ability to download clean snapshot

---------

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>

docs/docs/configuration/reference.md

@@ -710,6 +710,44 @@ audio_transcription:
   # List of language codes: https://github.com/openai/whisper/blob/main/whisper/tokenizer.py#L10
   language: en
 
+# Optional: Configuration for classification models
+classification:
+  # Optional: Configuration for bird classification
+  bird:
+    # Optional: Enable bird classification (default: shown below)
+    enabled: False
+    # Optional: Minimum classification score required to be considered a match (default: shown below)
+    threshold: 0.9
+  custom:
+    # Required: name of the classification model
+    model_name:
+      # Optional: Enable running the model (default: shown below)
+      enabled: True
+      # Optional: Name of classification model (default: shown below)
+      name: None
+      # Optional: Classification score threshold to change the state (default: shown below)
+      threshold: 0.8
+      # Optional: Number of classification attempts to save in the recent classifications tab (default: shown below)
+      # NOTE: Defaults to 200 for object classification and 100 for state classification if not specified
+      save_attempts: None
+      # Optional: Object classification configuration
+      object_config:
+        # Required: Object types to classify
+        objects: [dog]
+        # Optional: Type of classification that is applied (default: shown below)
+        classification_type: sub_label
+      # Optional: State classification configuration
+      state_config:
+        # Required: Cameras to run classification on
+        cameras:
+          camera_name:
+            # Required: Crop of image frame on this camera to run classification on
+            crop: [0, 180, 220, 400]
+        # Optional: If classification should be run when motion is detected in the crop (default: shown below)
+        motion: False
+        # Optional: Interval to run classification on in seconds (default: shown below)
+        interval: None
+
 # Optional: Restream configuration
 # Uses https://github.com/AlexxIT/go2rtc (v1.9.10)
 # NOTE: The default go2rtc API port (1984) must be used,