heimoshuiyu/faster-whisper
1
0
Fork 0
Code Issues Pull Requests 1 Packages Projects Releases Wiki Activity

Invalidate the cached encoder output when no_speech threshold is met (#376)

Browse Source
This commit is contained in:
Guillaume Klein
2023-07-24 10:57:15 +02:00
committed by GitHub
parent e786e26f75
commit 0f55c436fe
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
faster_whisper/transcribe.py
View File

@@ -422,6 +422,7 @@ class WhisperModel:
# fast-forward to the next segment boundary # fast-forward to the next segment boundary
seek += segment_size seek += segment_size
encoder_output = None
continue continue
tokens = result.sequences_ids[0] tokens = result.sequences_ids[0]