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
This commit is contained in:
Josh Hawkins
2025-05-27 10:26:00 -05:00
committed by Blake Blackshear
parent 2385c403ee
commit 6dc36fcbb4
29 changed files with 2322 additions and 51 deletions

View File

@@ -139,7 +139,7 @@ Message published for updates to tracked object metadata, for example:
"name": "John",
"score": 0.95,
"camera": "front_door_cam",
"timestamp": 1607123958.748393,
"timestamp": 1607123958.748393
}
```
@@ -153,7 +153,7 @@ Message published for updates to tracked object metadata, for example:
"plate": "123ABC",
"score": 0.95,
"camera": "driveway_cam",
"timestamp": 1607123958.748393,
"timestamp": 1607123958.748393
}
```
@@ -269,6 +269,12 @@ Publishes the rms value for audio detected on this camera.
**NOTE:** Requires audio detection to be enabled
### `frigate/<camera_name>/audio/transcription`
Publishes transcribed text for audio detected on this camera.
**NOTE:** Requires audio detection and transcription to be enabled
### `frigate/<camera_name>/enabled/set`
Topic to turn Frigate's processing of a camera on and off. Expected values are `ON` and `OFF`.