administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-08-02 09:02:15 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Fix audio transcription (#20395)
CI / AMD64 Build (push) Waiting to run
Details
CI / ARM Build (push) Waiting to run
Details
CI / Jetson Jetpack 6 (push) Waiting to run
Details
CI / AMD64 Extra Build (push) Blocked by required conditions
Details
CI / ARM Extra Build (push) Blocked by required conditions
Details
CI / Synaptics Build (push) Blocked by required conditions
Details
CI / Assemble and push default build (push) Blocked by required conditions
Details

Browse Source 
* 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
This commit is contained in:
Josh Hawkins
2025-10-08 18:06:03 -05:00
committed by GitHub
parent c71e235b38
commit c61bb8f8ae
7 changed files with 33 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
frigate/config/camera/camera.py
+4 -3
View File
@@ -19,7 +19,7 @@ from frigate.util.builtin import (
from ..base import FrigateBaseModel
from ..classification import (
AudioTranscriptionConfig,
CameraAudioTranscriptionConfig,
CameraFaceRecognitionConfig,
CameraLicensePlateRecognitionConfig,
CameraSemanticSearchConfig,
@@ -69,8 +69,9 @@ class CameraConfig(FrigateBaseModel):
audio: AudioConfig = Field(
default_factory=AudioConfig, title="Audio events configuration."
)
audio_transcription: AudioTranscriptionConfig = Field(
default_factory=AudioTranscriptionConfig, title="Audio transcription config."
audio_transcription: CameraAudioTranscriptionConfig = Field(
default_factory=CameraAudioTranscriptionConfig,
title="Audio transcription config.",
)
birdseye: BirdseyeCameraConfig = Field(
default_factory=BirdseyeCameraConfig, title="Birdseye camera configuration."
frigate/config/classification.py
+14 -4
View File
@@ -8,6 +8,7 @@ from .base import FrigateBaseModel
__all__ = [
"CameraFaceRecognitionConfig",
"CameraLicensePlateRecognitionConfig",
"CameraAudioTranscriptionConfig",
"FaceRecognitionConfig",
"SemanticSearchConfig",
"CameraSemanticSearchConfig",
@@ -47,14 +48,11 @@ class AudioTranscriptionConfig(FrigateBaseModel):
)
device: Optional[EnrichmentsDeviceEnum] = Field(
default=EnrichmentsDeviceEnum.CPU,
title="The device used for license plate recognition.",
title="The device used for audio transcription.",
)
model_size: str = Field(
default="small", title="The size of the embeddings model used."
)
enabled_in_config: Optional[bool] = Field(
default=None, title="Keep track of original state of camera."
)
live_enabled: Optional[bool] = Field(
default=False, title="Enable live transcriptions."
)
@@ -304,3 +302,15 @@ class CameraLicensePlateRecognitionConfig(FrigateBaseModel):
)
model_config = ConfigDict(extra="forbid", protected_namespaces=())
class CameraAudioTranscriptionConfig(FrigateBaseModel):
enabled: bool = Field(default=False, title="Enable audio transcription.")
enabled_in_config: Optional[bool] = Field(
default=None, title="Keep track of original state of audio transcription."
)
live_enabled: Optional[bool] = Field(
default=False, title="Enable live transcriptions."
)
model_config = ConfigDict(extra="forbid", protected_namespaces=())