appleboy/Speech to Text OpenAI Whisper

High-performance inference of OpenAI Whisper automatic speech recognition (ASR) model

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
modelpublic whisper model. (available: small, medium and large)small
audio_pathAudio Path.
output_folderoutput folder.
output_formatoutput format, support txt, srt, csv.txt
output_filenameoutput filename.
debugenable debug mode.
print_progressprint progress.true
print_segmentprint segment.
youtube_urlyoutube url
translatetranslate from source language to english
cut_silencescut silences
promptinitial prompt

no outputs