selfhostyourtech/reflector
2
0
Fork 0
mirror of https://github.com/Monadical-SAS/reflector.git synced 2025-12-20 12:19:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: parakeet vad not getting the end timestamp (#728)

Browse Source
This commit is contained in:
Mathieu Virbel
2025-11-18 09:15:29 -06:00
committed by GitHub
parent 2801ab3643
commit 18ed713369
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
gpu/modal_deployments/reflector_transcriber_parakeet.py
View File

@@ -81,9 +81,9 @@ image = (
"cuda-python==12.8.0", "cuda-python==12.8.0",
"fastapi==0.115.12", "fastapi==0.115.12",
"numpy<2", "numpy<2",
"librosa==0.10.1", "librosa==0.11.0",
"requests", "requests",
"silero-vad==5.1.0", "silero-vad==6.2.0",
"torch", "torch",
) )
.entrypoint([]) # silence chatty logs by container on start .entrypoint([]) # silence chatty logs by container on start
@@ -306,6 +306,7 @@ class TranscriberParakeetFile:
) -> Generator[TimeSegment, None, None]: ) -> Generator[TimeSegment, None, None]:
"""Generate speech segments using VAD with start/end sample indices""" """Generate speech segments using VAD with start/end sample indices"""
vad_iterator = VADIterator(self.vad_model, sampling_rate=SAMPLERATE) vad_iterator = VADIterator(self.vad_model, sampling_rate=SAMPLERATE)
audio_duration = len(audio_array) / float(SAMPLERATE)
window_size = VAD_CONFIG["window_size"] window_size = VAD_CONFIG["window_size"]
start = None start = None
@@ -332,6 +333,10 @@ class TranscriberParakeetFile:
yield TimeSegment(start_time, end_time) yield TimeSegment(start_time, end_time)
start = None start = None
if start is not None:
start_time = start / float(SAMPLERATE)
yield TimeSegment(start_time, audio_duration)
vad_iterator.reset_states() vad_iterator.reset_states()
def batch_speech_segments( def batch_speech_segments(