Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-02-20 13:54:36 +01:00
Code Issues Projects Releases Wiki Activity

Fix audio transcription (#20395)

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

2
frigate/data_processing/real_time/whisper_online.py
View File

@@ -141,6 +141,8 @@ class FasterWhisperASR(ASRBase):
def transcribe(self, audio, init_prompt=""):
from faster_whisper import BatchedInferencePipeline
logging.getLogger("faster_whisper").setLevel(logging.WARNING)
# tested: beam_size=5 is faster and better than 1 (on one 200 second document from En ESIC, min chunk 0.01)
batched_model = BatchedInferencePipeline(model=self.model)
segments, info = batched_model.transcribe(