admin-valentin/WhisperLiveKit
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

trim will happen before audio processor

Browse source
This commit is contained in:
Quentin Fuxa 2025-08-27 18:17:11 +02:00
parent f9c9c4188a
commit ab98c31f16
1 changed files with 0 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
whisperlivekit/audio_processor.py
View file

@ -4,12 +4,9 @@ from time import time, sleep
import math import math
import logging import logging
import traceback import traceback
from datetime import timedelta
from whisperlivekit.timed_objects import ASRToken, Silence from whisperlivekit.timed_objects import ASRToken, Silence
from whisperlivekit.core import TranscriptionEngine, online_factory, online_diarization_factory from whisperlivekit.core import TranscriptionEngine, online_factory, online_diarization_factory
from whisperlivekit.ffmpeg_manager import FFmpegManager, FFmpegState from whisperlivekit.ffmpeg_manager import FFmpegManager, FFmpegState
from whisperlivekit.remove_silences import handle_silences
from whisperlivekit.trail_repetition import trim_tail_repetition
from whisperlivekit.silero_vad_iterator import FixedVADIterator from whisperlivekit.silero_vad_iterator import FixedVADIterator
from whisperlivekit.results_formater import format_output, format_time from whisperlivekit.results_formater import format_output, format_time
# Set up logging once # Set up logging once
@ -109,17 +106,6 @@ class AudioProcessor:
"""Thread-safe update of transcription with new data.""" """Thread-safe update of transcription with new data."""
async with self.lock: async with self.lock:
self.tokens.extend(new_tokens) self.tokens.extend(new_tokens)
# self.tokens, has_been_trimmed = trim_tail_repetition(
# self.tokens,
# key=lambda t: t.text.strip().lower(),
# min_block=2, # avoid trimming single '.' loops; set to 1 if you want to remove those too
# max_tail=200,
# prefer="longest", # prefer removing the longest repeated phrase
# keep=1
# )
# if has_been_trimmed:
# print('HAS BEEN TRIMMED !')
self.buffer_transcription = buffer self.buffer_transcription = buffer
self.end_buffer = end_buffer self.end_buffer = end_buffer
self.sep = sep self.sep = sep