We interviewed the Mozart of Gen Z - Colin and Samir
[Your heroes make things possible.]
[Finding your voice involves trying stuff; not possible to ‘contribute’ by waiting to find your voice first.]
[Try making the worst song ever.]
[A question culture versus answee culture.]
[Questions last longer than answers.]
[My room is my spaceship and I can command it to go wherever I want. My job is to tune in to the internal weather: what’s turning me on today?]
Jacob Collier edits his own videos?
Whisper or ‘Whisper-Faster’ can run as a standalone terminal program on macOS 10.14 with whisper-standalone-win by simply downloading the binary from ‘releases’ and running a single command from the resulting folder:
./whisper-faster "~/alfa/bravo.mp3" --pp --model base.en --language=en --output_format all --output_dir .
This will fetch the model if there isn’t a local copy, and transcribe into about half a dozen formats, including plaintext, JSON, and subtitle files.
The openai/whisper documentation says:
The .en models for English-only applications tend to perform better, especially for the tiny.en and base.en models. We observed that the difference becomes less significant for the small.en and medium.en models.
To run it without printing text into the console, use -pp or send to NUL