Crate rwhisper 

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.
    text.to_std_out().await.unwrap();

    Ok(())
}

Structs

ChunkedTranscriptionTask

A chunked audio transcription task which can be streamed from a Whisper model.

ParseWhisperLanguageError

Error that reports the unsupported value

ParseWhisperSourceError

Error that reports the unsupported value

Segment

A transcribed segment of audio.

TokenChunkRef

A reference to a utf8 token chunk in a segment.

TranscriptionTask

A transcription task which can be streamed from a Whisper model.

Whisper

A quantized whisper audio transcription model.

WhisperBuilder

A builder with configuration for a Whisper model.

Enums

FileSource

A source for a file, either from Hugging Face or a local path

ModelLoadingProgress

The progress starting a model

WhisperLanguage

A language whisper can use

WhisperSource

The source whisper model to use.

Traits

TranscribeChunkedAudioStreamExt

An extension trait to transcribe pre-chunked audio streams