im making a script that just extracts audio then add subtitles to a video. using faster-whisper and moviepy.
i did some benchmarking and these are the times,
=== BENCHMARK RESULTS ===
video_render 358.28s
word_extraction 34.11s
subtitle_creation 3.30s
model_init 0.44s
whisper_transcribe 0.44s
the code is below