Command-line usage
1). The following command will Transcribe speech in audio files, using the medium model:
!whisper audio.flac audio.mp3 audio.wav --model medium
The default setting (which selects the small model) works well for transcribing English. (The above will transcribe an English language file into English text script)
2) The following command will Transcribe speech in an Urdu or another language audio file to English script using the:
!whisper "/content/sample_data/sample_urdu1.mp3" --model medium --language en
(The above will transcribe an Urdu language input file into English text script)
3) The following command will Transcribe speech in an Urdu Audio file, using the medium model:
!whisper "/content/sample_data/sampleurdufile1.mp3" --model medium --language ur
(The above will transcribe an Urdu input file, into an Urdu script)
The following command will Transcribe speech in audio files, using the medium model:
!whisper audio.flac audio.mp3 audio.wav --model medium
The default setting (which selects the small model) works well for transcribing English.
To transcribe an audio file containing non-English speech, you can specify the language using the --language option:
!whisper filename.wav --language Japanese
To translate an Audio file from one language to another language use the --translate option
!whisper filename.wav --task translate --language en (will translate the speech into English)
Run the following command to view all available options:
!whisper --help
