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

Include duration in AudioInfo structure

Browse Source
This commit is contained in:
Guillaume Klein
2023-03-15 15:30:29 +01:00
parent c5f6b91b7d
commit ae9898f0d8
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
faster_whisper/transcribe.py
View File

@@ -31,6 +31,7 @@ class Segment(NamedTuple):
class AudioInfo(NamedTuple): class AudioInfo(NamedTuple):
language: str language: str
language_probability: float language_probability: float
duration: float
class TranscriptionOptions(NamedTuple): class TranscriptionOptions(NamedTuple):
@@ -193,6 +194,7 @@ class WhisperModel:
audio, sampling_rate=self.feature_extractor.sampling_rate audio, sampling_rate=self.feature_extractor.sampling_rate
) )
duration = audio.shape[0] / self.feature_extractor.sampling_rate
features = self.feature_extractor(audio) features = self.feature_extractor(audio)
if language is None: if language is None:
@@ -243,6 +245,7 @@ class WhisperModel:
audio_info = AudioInfo( audio_info = AudioInfo(
language=language, language=language,
language_probability=language_probability, language_probability=language_probability,
duration=duration,
) )
return segments, audio_info return segments, audio_info