Merge 1f5b7fb946 into 1a75251ffb

docs/docs/configuration/audio_detectors.md

@@ -157,3 +157,19 @@ Only one `speech` event may be transcribed at a time. Frigate does not automatic
 :::
 
 Recorded `speech` events will always use a `whisper` model, regardless of the `model_size` config setting. Without a supported Nvidia GPU, generating transcriptions for longer `speech` events may take a fair amount of time, so be patient.
+
+#### FAQ
+
+1. Why doesn't Frigate automatically transcribe all `speech` events?
+
+   Frigate does not implement a queue mechanism for speech transcription, and adding one is not trivial. A proper queue would need backpressure, prioritization, memory/disk buffering, retry logic, crash recovery, and safeguards to prevent unbounded growth when events outpace processing. That’s a significant amount of complexity for a feature that, in most real-world environments, would mostly just churn through low-value noise.
+
+   Because transcription is **serialized (one event at a time)** and speech events can be generated far faster than they can be processed, an auto-transcribe toggle would very quickly create an ever-growing backlog and degrade core functionality. For the amount of engineering and risk involved, it adds **very little practical value** for the majority of deployments, which are often on low-powered, edge hardware.
+
+   If you hear speech that’s actually important and worth saving/indexing for the future, **just press the transcribe button in Explore** on that specific `speech` event - that keeps things explicit, reliable, and under your control.
+
+2. Why don't you save live transcription text and use that for `speech` events?
+
+   There’s no guarantee that a `speech` event is even created from the exact audio that went through the transcription model. Live transcription and `speech` event creation are **separate, asynchronous processes**. Even when both are correctly configured, trying to align the **precise start and end time of a speech event** with whatever audio the model happened to be processing at that moment is unreliable.
+
+   Automatically persisting that data would often result in **misaligned, partial, or irrelevant transcripts**, while still incurring all of the CPU, storage, and privacy costs of transcription. That’s why Frigate treats transcription as an **explicit, user-initiated action** rather than an automatic side-effect of every `speech` event.

frigate/data_processing/real_time/custom_classification.py

@@ -99,6 +99,42 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
         if self.inference_speed:
             self.inference_speed.update(duration)
 
+    def _should_save_image(
+        self, camera: str, detected_state: str, score: float = 1.0
+    ) -> bool:
+        """
+        Determine if we should save the image for training.
+        Save when:
+        - State is changing or being verified (regardless of score)
+        - Score is less than 100% (even if state matches, useful for training)
+        Don't save when:
+        - State is stable (matches current_state) AND score is 100%
+        """
+        if camera not in self.state_history:
+            # First detection for this camera, save it
+            return True
+
+        verification = self.state_history[camera]
+        current_state = verification.get("current_state")
+        pending_state = verification.get("pending_state")
+
+        # Save if there's a pending state change being verified
+        if pending_state is not None:
+            return True
+
+        # Save if the detected state differs from the current verified state
+        # (state is changing)
+        if current_state is not None and detected_state != current_state:
+            return True
+
+        # If score is less than 100%, save even if state matches
+        # (useful for training to improve confidence)
+        if score < 1.0:
+            return True
+
+        # Don't save if state is stable (detected_state == current_state) AND score is 100%
+        return False
+
     def verify_state_change(self, camera: str, detected_state: str) -> str | None:
         """
         Verify state change requires 3 consecutive identical states before publishing.
@@ -212,6 +248,8 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
                 return
 
         if self.interpreter is None:
+            # When interpreter is None, always save (score is 0.0, which is < 1.0)
+            if self._should_save_image(camera, "unknown", 0.0):
                 write_classification_attempt(
                     self.train_dir,
                     cv2.cvtColor(frame, cv2.COLOR_RGB2BGR),
@@ -236,12 +274,15 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
         score = round(probs[best_id], 2)
         self.__update_metrics(datetime.datetime.now().timestamp() - now)
 
+        detected_state = self.labelmap[best_id]
+
+        if self._should_save_image(camera, detected_state, score):
             write_classification_attempt(
                 self.train_dir,
                 cv2.cvtColor(frame, cv2.COLOR_RGB2BGR),
                 "none-none",
                 now,
-            self.labelmap[best_id],
+                detected_state,
                 score,
             )
 
@@ -251,7 +292,6 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
             )
             return
 
-        detected_state = self.labelmap[best_id]
         verified_state = self.verify_state_change(camera, detected_state)
 
         if verified_state is not None:

frigate/ptz/onvif.py

@@ -190,7 +190,11 @@ class OnvifController:
         ptz: ONVIFService = await onvif.create_ptz_service()
         self.cams[camera_name]["ptz"] = ptz
 
+        try:
             imaging: ONVIFService = await onvif.create_imaging_service()
+        except (Fault, ONVIFError, TransportError, Exception) as e:
+            logger.debug(f"Imaging service not supported for {camera_name}: {e}")
+            imaging = None
         self.cams[camera_name]["imaging"] = imaging
         try:
             video_sources = await media.GetVideoSources()
@@ -381,7 +385,10 @@ class OnvifController:
                             f"Disabling autotracking zooming for {camera_name}: Absolute zoom not supported. Exception: {e}"
                         )
 
-        if self.cams[camera_name]["video_source_token"] is not None:
+        if (
+            self.cams[camera_name]["video_source_token"] is not None
+            and imaging is not None
+        ):
             try:
                 imaging_capabilities = await imaging.GetImagingSettings(
                     {"VideoSourceToken": self.cams[camera_name]["video_source_token"]}
@@ -421,6 +428,7 @@ class OnvifController:
         if (
             "focus" in self.cams[camera_name]["features"]
             and self.cams[camera_name]["video_source_token"]
+            and self.cams[camera_name]["imaging"] is not None
         ):
             try:
                 stop_request = self.cams[camera_name]["imaging"].create_type("Stop")
@@ -648,6 +656,7 @@ class OnvifController:
         if (
             "focus" not in self.cams[camera_name]["features"]
             or not self.cams[camera_name]["video_source_token"]
+            or self.cams[camera_name]["imaging"] is None
         ):
             logger.error(f"{camera_name} does not support ONVIF continuous focus.")
             return

web/src/components/classification/ClassificationModelEditDialog.tsx

@@ -37,7 +37,7 @@ import { useForm } from "react-hook-form";
 import { useTranslation } from "react-i18next";
 import { LuPlus, LuX } from "react-icons/lu";
 import { toast } from "sonner";
-import useSWR from "swr";
+import useSWR, { mutate } from "swr";
 import { z } from "zod";
 
 type ClassificationModelEditDialogProps = {
@@ -240,24 +240,72 @@ export default function ClassificationModelEditDialog({
             position: "top-center",
           });
         } else {
-          // State model - update classes
+          const stateData = data as StateFormData;
-          // Note: For state models, updating classes requires renaming categories
+          const newClasses = stateData.classes.filter(
-          // which is handled through the dataset API, not the config API
+            (c) => c.trim().length > 0,
-          // We'll need to implement this by calling the rename endpoint for each class
+          );
-          // For now, we just show a message that this requires retraining
+          const oldClasses = dataset?.categories
+            ? Object.keys(dataset.categories).filter((key) => key !== "none")
+            : [];
 
+          const renameMap = new Map<string, string>();
+          const maxLength = Math.max(oldClasses.length, newClasses.length);
+
+          for (let i = 0; i < maxLength; i++) {
+            const oldClass = oldClasses[i];
+            const newClass = newClasses[i];
+
+            if (oldClass && newClass && oldClass !== newClass) {
+              renameMap.set(oldClass, newClass);
+            }
+          }
+
+          const renamePromises = Array.from(renameMap.entries()).map(
+            async ([oldName, newName]) => {
+              try {
+                await axios.put(
+                  `/classification/${model.name}/dataset/${oldName}/rename`,
+                  {
+                    new_category: newName,
+                  },
+                );
+              } catch (err) {
+                const error = err as {
+                  response?: { data?: { message?: string; detail?: string } };
+                };
+                const errorMessage =
+                  error.response?.data?.message ||
+                  error.response?.data?.detail ||
+                  "Unknown error";
+                throw new Error(
+                  `Failed to rename ${oldName} to ${newName}: ${errorMessage}`,
+                );
+              }
+            },
+          );
+
+          if (renamePromises.length > 0) {
+            await Promise.all(renamePromises);
+            await mutate(`classification/${model.name}/dataset`);
+            toast.success(t("toast.success.updatedModel"), {
+              position: "top-center",
+            });
+          } else {
             toast.info(t("edit.stateClassesInfo"), {
               position: "top-center",
             });
           }
+        }
 
         onSuccess();
         onClose();
       } catch (err) {
         const error = err as {
           response?: { data?: { message?: string; detail?: string } };
+          message?: string;
         };
         const errorMessage =
+          error.message ||
           error.response?.data?.message ||
           error.response?.data?.detail ||
           "Unknown error";
@@ -268,7 +316,7 @@ export default function ClassificationModelEditDialog({
         setIsSaving(false);
       }
     },
-    [isObjectModel, model, t, onSuccess, onClose],
+    [isObjectModel, model, dataset, t, onSuccess, onClose],
   );
 
   const handleCancel = useCallback(() => {

web/src/components/menu/LiveContextMenu.tsx

@@ -48,6 +48,7 @@ import { useTranslation } from "react-i18next";
 import { useDateLocale } from "@/hooks/use-date-locale";
 import { useIsAdmin } from "@/hooks/use-is-admin";
 import { CameraNameLabel } from "../camera/FriendlyNameLabel";
+import { LiveStreamMetadata } from "@/types/live";
 
 type LiveContextMenuProps = {
   className?: string;
@@ -68,6 +69,7 @@ type LiveContextMenuProps = {
   resetPreferredLiveMode: () => void;
   config?: FrigateConfig;
   children?: ReactNode;
+  streamMetadata?: { [key: string]: LiveStreamMetadata };
 };
 export default function LiveContextMenu({
   className,
@@ -88,6 +90,7 @@ export default function LiveContextMenu({
   resetPreferredLiveMode,
   config,
   children,
+  streamMetadata,
 }: LiveContextMenuProps) {
   const { t } = useTranslation("views/live");
   const [showSettings, setShowSettings] = useState(false);
@@ -558,6 +561,7 @@ export default function LiveContextMenu({
           setGroupStreamingSettings={setGroupStreamingSettings}
           setIsDialogOpen={setShowSettings}
           onSave={onSave}
+          streamMetadata={streamMetadata}
         />
       </Dialog>
     </div>

web/src/components/settings/CameraStreamingDialog.tsx

@@ -38,6 +38,7 @@ import { useCameraFriendlyName } from "@/hooks/use-camera-friendly-name";
 type CameraStreamingDialogProps = {
   camera: string;
   groupStreamingSettings: GroupStreamingSettings;
+  streamMetadata?: { [key: string]: LiveStreamMetadata };
   setGroupStreamingSettings: React.Dispatch<
     React.SetStateAction<GroupStreamingSettings>
   >;
@@ -48,6 +49,7 @@ type CameraStreamingDialogProps = {
 export function CameraStreamingDialog({
   camera,
   groupStreamingSettings,
+  streamMetadata,
   setGroupStreamingSettings,
   setIsDialogOpen,
   onSave,
@@ -76,12 +78,7 @@ export function CameraStreamingDialog({
     [config, streamName],
   );
 
-  const { data: cameraMetadata } = useSWR<LiveStreamMetadata>(
+  const cameraMetadata = streamName ? streamMetadata?.[streamName] : undefined;
-    isRestreamed ? `go2rtc/streams/${streamName}` : null,
-    {
-      revalidateOnFocus: false,
-    },
-  );
 
   const supportsAudioOutput = useMemo(() => {
     if (!cameraMetadata) {

web/src/hooks/use-camera-live-mode.ts

@@ -1,8 +1,8 @@
-import { baseUrl } from "@/api/baseUrl";
 import { CameraConfig, FrigateConfig } from "@/types/frigateConfig";
 import { useCallback, useEffect, useState, useMemo } from "react";
 import useSWR from "swr";
-import { LivePlayerMode, LiveStreamMetadata } from "@/types/live";
+import { LivePlayerMode } from "@/types/live";
+import useDeferredStreamMetadata from "./use-deferred-stream-metadata";
 
 export default function useCameraLiveMode(
   cameras: CameraConfig[],
@@ -11,9 +11,9 @@ export default function useCameraLiveMode(
 ) {
   const { data: config } = useSWR<FrigateConfig>("config");
 
-  // Get comma-separated list of restreamed stream names for SWR key
+  // Compute which streams need metadata (restreamed streams only)
-  const restreamedStreamsKey = useMemo(() => {
+  const restreamedStreamNames = useMemo(() => {
-    if (!cameras || !config) return null;
+    if (!cameras || !config) return [];
 
     const streamNames = new Set<string>();
     cameras.forEach((camera) => {
@@ -32,56 +32,13 @@ export default function useCameraLiveMode(
       }
     });
 
-    return streamNames.size > 0
+    return Array.from(streamNames);
-      ? Array.from(streamNames).sort().join(",")
-      : null;
   }, [cameras, config, activeStreams]);
 
-  const streamsFetcher = useCallback(async (key: string) => {
+  // Fetch stream metadata with deferred loading (doesn't block initial render)
-    const streamNames = key.split(",");
+  const streamMetadata = useDeferredStreamMetadata(restreamedStreamNames);
-
-    const metadataPromises = streamNames.map(async (streamName) => {
-      try {
-        const response = await fetch(
-          `${baseUrl}api/go2rtc/streams/${streamName}`,
-          {
-            priority: "low",
-          },
-        );
-
-        if (response.ok) {
-          const data = await response.json();
-          return { streamName, data };
-        }
-        return { streamName, data: null };
-      } catch (error) {
-        // eslint-disable-next-line no-console
-        console.error(`Failed to fetch metadata for ${streamName}:`, error);
-        return { streamName, data: null };
-      }
-    });
-
-    const results = await Promise.allSettled(metadataPromises);
-
-    const metadata: { [key: string]: LiveStreamMetadata } = {};
-    results.forEach((result) => {
-      if (result.status === "fulfilled" && result.value.data) {
-        metadata[result.value.streamName] = result.value.data;
-      }
-    });
-
-    return metadata;
-  }, []);
-
-  const { data: allStreamMetadata = {} } = useSWR<{
-    [key: string]: LiveStreamMetadata;
-  }>(restreamedStreamsKey, streamsFetcher, {
-    revalidateOnFocus: false,
-    revalidateOnReconnect: false,
-    revalidateIfStale: false,
-    dedupingInterval: 60000,
-  });
 
+  // Compute live mode states
   const [preferredLiveModes, setPreferredLiveModes] = useState<{
     [key: string]: LivePlayerMode;
   }>({});
@@ -122,10 +79,10 @@ export default function useCameraLiveMode(
         newPreferredLiveModes[camera.name] = isRestreamed ? "mse" : "jsmpeg";
       }
 
-      // check each stream for audio support
+      // Check each stream for audio support
       if (isRestreamed) {
         Object.values(camera.live.streams).forEach((streamName) => {
-          const metadata = allStreamMetadata?.[streamName];
+          const metadata = streamMetadata[streamName];
           newSupportsAudioOutputStates[streamName] = {
             supportsAudio: metadata
               ? metadata.producers.find(
@@ -150,7 +107,7 @@ export default function useCameraLiveMode(
     setPreferredLiveModes(newPreferredLiveModes);
     setIsRestreamedStates(newIsRestreamedStates);
     setSupportsAudioOutputStates(newSupportsAudioOutputStates);
-  }, [cameras, config, windowVisible, allStreamMetadata]);
+  }, [cameras, config, windowVisible, streamMetadata]);
 
   const resetPreferredLiveMode = useCallback(
     (cameraName: string) => {
@@ -180,5 +137,6 @@ export default function useCameraLiveMode(
     resetPreferredLiveMode,
     isRestreamedStates,
     supportsAudioOutputStates,
+    streamMetadata,
   };
 }

web/src/hooks/use-deferred-stream-metadata.ts

@@ -0,0 +1,90 @@
+import { baseUrl } from "@/api/baseUrl";
+import { useCallback, useEffect, useState, useMemo } from "react";
+import useSWR from "swr";
+import { LiveStreamMetadata } from "@/types/live";
+
+const FETCH_TIMEOUT_MS = 10000;
+const DEFER_DELAY_MS = 2000;
+
+/**
+ * Hook that fetches go2rtc stream metadata with deferred loading.
+ *
+ * Metadata fetching is delayed to prevent blocking initial page load
+ * and camera image requests.
+ *
+ * @param streamNames - Array of stream names to fetch metadata for
+ * @returns Object containing stream metadata keyed by stream name
+ */
+export default function useDeferredStreamMetadata(streamNames: string[]) {
+  const [fetchEnabled, setFetchEnabled] = useState(false);
+
+  useEffect(() => {
+    const timeoutId = setTimeout(() => {
+      setFetchEnabled(true);
+    }, DEFER_DELAY_MS);
+
+    return () => clearTimeout(timeoutId);
+  }, []);
+
+  const swrKey = useMemo(() => {
+    if (!fetchEnabled || streamNames.length === 0) return null;
+    // Use spread to avoid mutating the original array
+    return `deferred-streams:${[...streamNames].sort().join(",")}`;
+  }, [fetchEnabled, streamNames]);
+
+  const fetcher = useCallback(async (key: string) => {
+    // Extract stream names from key (remove prefix)
+    const names = key.replace("deferred-streams:", "").split(",");
+
+    const promises = names.map(async (streamName) => {
+      const controller = new AbortController();
+      const timeoutId = setTimeout(() => controller.abort(), FETCH_TIMEOUT_MS);
+
+      try {
+        const response = await fetch(
+          `${baseUrl}api/go2rtc/streams/${streamName}`,
+          {
+            priority: "low",
+            signal: controller.signal,
+          },
+        );
+        clearTimeout(timeoutId);
+
+        if (response.ok) {
+          const data = await response.json();
+          return { streamName, data };
+        }
+        return { streamName, data: null };
+      } catch (error) {
+        clearTimeout(timeoutId);
+        if ((error as Error).name !== "AbortError") {
+          // eslint-disable-next-line no-console
+          console.error(`Failed to fetch metadata for ${streamName}:`, error);
+        }
+        return { streamName, data: null };
+      }
+    });
+
+    const results = await Promise.allSettled(promises);
+
+    const metadata: { [key: string]: LiveStreamMetadata } = {};
+    results.forEach((result) => {
+      if (result.status === "fulfilled" && result.value.data) {
+        metadata[result.value.streamName] = result.value.data;
+      }
+    });
+
+    return metadata;
+  }, []);
+
+  const { data: metadata = {} } = useSWR<{
+    [key: string]: LiveStreamMetadata;
+  }>(swrKey, fetcher, {
+    revalidateOnFocus: false,
+    revalidateOnReconnect: false,
+    revalidateIfStale: false,
+    dedupingInterval: 60000,
+  });
+
+  return metadata;
+}

web/src/views/live/DraggableGridLayout.tsx

@@ -24,6 +24,7 @@ import "react-resizable/css/styles.css";
 import {
   AudioState,
   LivePlayerMode,
+  LiveStreamMetadata,
   StatsState,
   VolumeState,
 } from "@/types/live";
@@ -47,7 +48,6 @@ import {
   TooltipContent,
 } from "@/components/ui/tooltip";
 import { Toaster } from "@/components/ui/sonner";
-import useCameraLiveMode from "@/hooks/use-camera-live-mode";
 import LiveContextMenu from "@/components/menu/LiveContextMenu";
 import { useStreamingSettings } from "@/context/streaming-settings-provider";
 import { useTranslation } from "react-i18next";
@@ -65,6 +65,16 @@ type DraggableGridLayoutProps = {
   setIsEditMode: React.Dispatch<React.SetStateAction<boolean>>;
   fullscreen: boolean;
   toggleFullscreen: () => void;
+  preferredLiveModes: { [key: string]: LivePlayerMode };
+  setPreferredLiveModes: React.Dispatch<
+    React.SetStateAction<{ [key: string]: LivePlayerMode }>
+  >;
+  resetPreferredLiveMode: (cameraName: string) => void;
+  isRestreamedStates: { [key: string]: boolean };
+  supportsAudioOutputStates: {
+    [key: string]: { supportsAudio: boolean; cameraName: string };
+  };
+  streamMetadata: { [key: string]: LiveStreamMetadata };
 };
 export default function DraggableGridLayout({
   cameras,
@@ -79,6 +89,12 @@ export default function DraggableGridLayout({
   setIsEditMode,
   fullscreen,
   toggleFullscreen,
+  preferredLiveModes,
+  setPreferredLiveModes,
+  resetPreferredLiveMode,
+  isRestreamedStates,
+  supportsAudioOutputStates,
+  streamMetadata,
 }: DraggableGridLayoutProps) {
   const { t } = useTranslation(["views/live"]);
   const { data: config } = useSWR<FrigateConfig>("config");
@@ -98,33 +114,6 @@ export default function DraggableGridLayout({
     }
   }, [allGroupsStreamingSettings, cameraGroup]);
 
-  const activeStreams = useMemo(() => {
-    const streams: { [cameraName: string]: string } = {};
-    cameras.forEach((camera) => {
-      const availableStreams = camera.live.streams || {};
-      const streamNameFromSettings =
-        currentGroupStreamingSettings?.[camera.name]?.streamName || "";
-      const streamExists =
-        streamNameFromSettings &&
-        Object.values(availableStreams).includes(streamNameFromSettings);
-
-      const streamName = streamExists
-        ? streamNameFromSettings
-        : Object.values(availableStreams)[0] || "";
-
-      streams[camera.name] = streamName;
-    });
-    return streams;
-  }, [cameras, currentGroupStreamingSettings]);
-
-  const {
-    preferredLiveModes,
-    setPreferredLiveModes,
-    resetPreferredLiveMode,
-    isRestreamedStates,
-    supportsAudioOutputStates,
-  } = useCameraLiveMode(cameras, windowVisible, activeStreams);
-
   // grid layout
 
   const ResponsiveGridLayout = useMemo(() => WidthProvider(Responsive), []);
@@ -624,6 +613,7 @@ export default function DraggableGridLayout({
                     resetPreferredLiveMode(camera.name)
                   }
                   config={config}
+                  streamMetadata={streamMetadata}
                 >
                   <LivePlayer
                     key={camera.name}
@@ -838,6 +828,7 @@ type GridLiveContextMenuProps = {
   unmuteAll: () => void;
   resetPreferredLiveMode: () => void;
   config?: FrigateConfig;
+  streamMetadata?: { [key: string]: LiveStreamMetadata };
 };
 
 const GridLiveContextMenu = React.forwardRef<
@@ -868,6 +859,7 @@ const GridLiveContextMenu = React.forwardRef<
       unmuteAll,
       resetPreferredLiveMode,
       config,
+      streamMetadata,
       ...props
     },
     ref,
@@ -899,6 +891,7 @@ const GridLiveContextMenu = React.forwardRef<
           unmuteAll={unmuteAll}
           resetPreferredLiveMode={resetPreferredLiveMode}
           config={config}
+          streamMetadata={streamMetadata}
         >
           {children}
         </LiveContextMenu>

web/src/views/live/LiveDashboardView.tsx

@@ -265,6 +265,7 @@ export default function LiveDashboardView({
     resetPreferredLiveMode,
     isRestreamedStates,
     supportsAudioOutputStates,
+    streamMetadata,
   } = useCameraLiveMode(cameras, windowVisible, activeStreams);
 
   const birdseyeConfig = useMemo(() => config?.birdseye, [config]);
@@ -650,6 +651,12 @@ export default function LiveDashboardView({
               setIsEditMode={setIsEditMode}
               fullscreen={fullscreen}
               toggleFullscreen={toggleFullscreen}
+              preferredLiveModes={preferredLiveModes}
+              setPreferredLiveModes={setPreferredLiveModes}
+              resetPreferredLiveMode={resetPreferredLiveMode}
+              isRestreamedStates={isRestreamedStates}
+              supportsAudioOutputStates={supportsAudioOutputStates}
+              streamMetadata={streamMetadata}
             />
           )}
         </>

web/src/views/settings/AuthenticationView.tsx

@@ -478,8 +478,7 @@ export default function AuthenticationView({
                       <TableCell className="text-right">
                         <TooltipProvider>
                           <div className="flex items-center justify-end gap-2">
-                            {user.username !== "admin" &&
+                            {user.username !== "admin" && (
-                              user.username !== "viewer" && (
                               <Tooltip>
                                 <TooltipTrigger asChild>
                                   <Button