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

Removed duplicate variable self.last_chunked_at

Browse source 
I tried to find the difference between self.last_chunked_at and self.buffer_time_offset, and it took me a while to understand that they are exactly the same. I think it's better to get rid of one of the duplicates to make the code more readable.
This commit is contained in:
Aleksei Scripnic 2024-01-03 10:06:05 +00:00 committed by Dominik Macháček
parent 949304ab05
commit 80eb0baf5d
1 changed files with 1 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
whisper_online.py
View file

@ -328,7 +328,6 @@ class OnlineASRProcessor:
self.transcript_buffer = HypothesisBuffer(logfile=self.logfile) self.transcript_buffer = HypothesisBuffer(logfile=self.logfile)
self.commited = [] self.commited = []
self.last_chunked_at = 0
self.silence_iters = 0 self.silence_iters = 0
@ -340,7 +339,7 @@ class OnlineASRProcessor:
"context" is the commited text that is inside the audio buffer. It is transcribed again and skipped. It is returned only for debugging and logging reasons. "context" is the commited text that is inside the audio buffer. It is transcribed again and skipped. It is returned only for debugging and logging reasons.
""" """
k = max(0,len(self.commited)-1) k = max(0,len(self.commited)-1)
while k > 0 and self.commited[k-1][1] > self.last_chunked_at: while k > 0 and self.commited[k-1][1] > self.buffer_time_offset:
k -= 1 k -= 1
p = self.commited[:k] p = self.commited[:k]
@ -451,7 +450,6 @@ class OnlineASRProcessor:
cut_seconds = time - self.buffer_time_offset cut_seconds = time - self.buffer_time_offset
self.audio_buffer = self.audio_buffer[int(cut_seconds*self.SAMPLING_RATE):] self.audio_buffer = self.audio_buffer[int(cut_seconds*self.SAMPLING_RATE):]
self.buffer_time_offset = time self.buffer_time_offset = time
self.last_chunked_at = time
def words_to_sentences(self, words): def words_to_sentences(self, words):
"""Uses self.tokenizer for sentence segmentation of words. """Uses self.tokenizer for sentence segmentation of words.