#whisper #transcription #ai

rwhisper

A simple interface for Whisper transcription models in Rust

10 releases

0.3.5 Aug 28, 2024
0.3.4 Aug 24, 2024
0.2.1 Feb 28, 2024
0.1.2 Dec 21, 2023

#474 in Audio

Download history 7/week @ 2024-08-05 260/week @ 2024-08-12 298/week @ 2024-08-19 171/week @ 2024-08-26 13/week @ 2024-09-02 9/week @ 2024-09-09 193/week @ 2024-09-16 110/week @ 2024-09-23 125/week @ 2024-09-30 38/week @ 2024-10-07 62/week @ 2024-10-14 31/week @ 2024-10-21 43/week @ 2024-10-28 21/week @ 2024-11-04 23/week @ 2024-11-11 48/week @ 2024-11-18

138 downloads per month
Used in 3 crates (via kalosm-sound)

MIT/Apache

505KB
4.5K SLoC

rwhisper

A Rust wrapper for whisper

Usage

use futures_util::StreamExt;
use kalosm::sound::*;
use tokio::time::{Duration, Instant};

#[tokio::main]
async fn main() -> Result<(), anyhow::Error> {
    // Create a new small whisper model.
    let model = WhisperBuilder::default()
        .with_source(WhisperSource::SmallEn)
        .build()
        .await?;

    // Record audio from the microphone for 5 seconds.
    let audio = MicInput::default()
        .record_until(Instant::now() + Duration::from_secs(5))
        .await?;

    // Transcribe the audio.
    let mut text = model.transcribe(audio)?;

    // As the model transcribes the audio, print the text to the console.
    while let Some(text) = text.next().await {
        print!("{}", text.text());
    }

    Ok(())
}

Dependencies

~36–75MB
~1.5M SLoC