A Whisper CLI, built with Rust

This project attempts to build a simple Whisper CLI with Rust, to replace the base Python one. It uses whisper.cpp under the hood, making it significantly faster on M1 systems.

Installation

You can download the binary corresponding to your OS from the latest release, or build it from scratch with cargo install whisper_cli.

Run from anywhere

Put the whisper binary in /usr/local/bin on Unix systems (Mac/Linux) & make sure it has permissions to execute (use chmod +x whisper in terminal.)

Close & Re-open the terminal to test it by typing whisper --help. It should output the following.

Usage

```bash $ whisper --help Generate a transcript of an audio file using the Whisper speech-to-text engine. The transcript will be saved as a .txt, .vtt, and .srt file in the same directory as the audio file.

Usage: whisper [OPTIONS]

Arguments:

Options: -m, --model Name of the Whisper model to use

      [default: medium]
      [possible values: tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large, large-v1]

-l, --lang Language spoken in the audio. Attempts to auto-detect by default

      [possible values: auto, en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, no, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, su]

-t, --translate Toggle translation

-k, --karaoke Generate timestamps for each word

-h, --help Print help information (use -h for a summary)

-V, --version Print version information ```

Develop

Make sure you have the latest version of rust installed (use rustup). Then, you can build the project by running cargo build, and run it with cargo run.

License

This project is licensed under the MIT License - see the LICENSE file for details.