#speech-recognition #stt

faster-whisper-rs

High-level rust bindings to the faster-whisper python api

2 unstable releases

0.2.0 Jul 15, 2024
0.1.0 Jun 2, 2024

#417 in Science

MIT/Apache

2MB
226 lines

faster-whisper-rs

It is a rust crate for easily implementing Speech-To-Text into your rust programs.

Python api:

faster-whisper

Install Rust

Install Rust

On Linux or MacOS:

curl --proto '=https' --tlsv1.2 -ssf https://sh.rustup.rs | sh

Example of making a transcript

use std::error::Error;
use faster-whisper-rs::WhisperModel;

fn main() -> Result<(), Box<dyn Error>>{
    let fw = WhisperModel::default();
    let transcript = fw.transcribe("Path to file".to_string())?;

    println!("{}", transcript);

    Ok(())
}

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

MIT

Dependencies

~4–9.5MB
~99K SLoC