cjones/WhisperLive
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Remove blank segment feature

Browse Source 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
This commit is contained in:
makaveli10
2025-04-17 08:29:14 +00:00
parent 617f587699
commit 9b364f267a
4 changed files with 3 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files
whisper_live/backend/trt_backend.py
+1 -3
View File
@@ -149,9 +149,7 @@ class ServeClientTensorRT(ServeClientBase):
If the client's language is not detected, it waits for 30 seconds of audio input to make a language prediction.
It utilizes the Whisper ASR model to transcribe the audio, continuously processing and streaming results. Segments
are sent to the client in real-time, and a history of segments is maintained to provide context.Pauses in speech
(no output from Whisper) are handled by showing the previous output for a set duration. A blank segment is added if
there is no speech for a specified duration to indicate a pause.
are sent to the client in real-time, and a history of segments is maintained to provide context.
Raises:
Exception: If there is an issue with audio processing or WebSocket communication.