CPP works on CPU only, but detection of English words is much much better than Faster Whisper (though most of the detected English words are transliterated in Arabic).My tests are done on mainly Arabic voice recordings that have many English terms and words within the narrative. ValueError: token was not found in the promptįile 'faster_whisper\transcribe.py', line 680, in generate_with_fallbackįile 'faster_whisper\transcribe.py', line 447, in generate_segmentsįile 'faster_whisper\transcribe.py', line 961, in restore_speech_timestampsįile 'D:\whisper-fast\_main_.py', line 622, in cliįile 'D:\whisper-fast\_main_.py', line 681, in Ĭalling whisper Purfview's Faster-Whisper done in 00:00:32.6182623 Failed to execute script '_main_' due to unhandled exception! Starting transcription on: C:\Users\nikse\AppData\Local\Temp\a5fa4bb4-3cca-4d5b-bb58-7522a6e9bb3e.wav Standalone Faster-Whisper r160.3 running on: CPU Message: Calling whisper (Purfview's Faster-Whisper) with : C:\git\subtitleedit\src\ui\bin\Debug\Whisper\Purfview-Whisper-Faster\whisper-faster.exe -language en -model 'large-v3' 'C:\Users\nikse\AppData\Local\Temp\a5fa4bb4-3cca-4d5b-bb58-7522a6e9bb3e.wav'
