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

Fix language detection with non-speech audio (#895)

Browse Source
This commit is contained in:
trungkienbkhn
2024-07-05 14:43:45 +07:00
committed by GitHub
parent 1195359984
commit fbcf58bf98
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
faster_whisper/transcribe.py
View File

@@ -390,7 +390,7 @@ class WhisperModel:
content_frames, content_frames,
) )
detected_language_info = {} detected_language_info = {}
while seek < end_frames: while seek <= end_frames:
segment = features[ segment = features[
:, seek : seek + self.feature_extractor.nb_max_frames :, seek : seek + self.feature_extractor.nb_max_frames
] ]