Player not loading? Watch on YouTube
This short demonstration uses Faster Whisper to generate a transcript from a video’s audio track. The speaker opens an accompanying repository, places a video in its media folder and runs a command copied from the documentation. The description links the Faster Whisper repository and the example script, 1_generate_transcript.py.
After processing finishes, the output is available as both a text file and a JSON file. The video follows that small workflow from input to output, without going through model selection or a full installation guide.
The run takes just under ten minutes. On the speaker’s machine, Faster Whisper processes roughly one minute of video per minute. The presenter notes that a faster computer would finish sooner; this example is a result from that setup rather than a general speed benchmark.
