No description
Find a file
0/0 68d9496924
Merge pull request #75 from wavey-ai/master
calculate mel.n_len as mel spectrogram stride len
2023-07-22 22:39:18 +00:00
.github/workflows move rustfmt into its own job as well 2023-05-05 21:57:03 -06:00
examples cargo fmt 2023-05-05 22:48:20 -06:00
src calculate mel.n_len as mel spectrogram stride len 2023-07-22 06:53:12 +01:00
sys Revert "don't remove bindings/javascript/package.json, it's a committed file in whisper.cpp" 2023-06-18 10:14:50 -06:00
.gitignore add all target directories to gitignore 2023-02-08 14:50:05 -07:00
.gitmodules Initial commit 2022-10-09 20:17:31 -06:00
BUILDING.md make sure the user has CMake installed 2023-05-14 16:58:37 -04:00
Cargo.toml update whisper-rs to 0.8.0 2023-05-14 14:34:53 -06:00
CHANGELOG.md update whisper-rs-sys to 0.6.1 2023-06-18 10:12:02 -06:00
LICENSE add LICENSE and README.md 2022-10-09 20:46:14 -06:00
README.md Add instructions for running the examples. 2023-06-18 18:19:33 +04:00

whisper-rs

Rust bindings to whisper.cpp

Usage

git clone --recursive https://github.com/tazz4843/whisper-rs.git

cd whisper-rs

cargo run --example basic_use

cargo run --example audio_transcription
use whisper_rs::{WhisperContext, FullParams, SamplingStrategy};

fn main() {
    let path_to_model = std::env::args().nth(1).unwrap();

    // load a context and model
    let ctx = WhisperContext::new(&path_to_model).expect("failed to load model");

    // create a params object
    let params = FullParams::new(SamplingStrategy::Greedy { best_of: 1 });

    // assume we have a buffer of audio data
    // here we'll make a fake one, floating point samples, 32 bit, 16KHz, mono
    let audio_data = vec![0_f32; 16000 * 2];

    // now we can run the model
    let mut state = ctx.create_state().expect("failed to create state");
    state
        .full(params, &audio_data[..])
        .expect("failed to run model");

    // fetch the results
    let num_segments = state
        .full_n_segments()
        .expect("failed to get number of segments");
    for i in 0..num_segments {
        let segment = state
            .full_get_segment_text(i)
            .expect("failed to get segment");
        let start_timestamp = state
            .full_get_segment_t0(i)
            .expect("failed to get segment start timestamp");
        let end_timestamp = state
            .full_get_segment_t1(i)
            .expect("failed to get segment end timestamp");
        println!("[{} - {}]: {}", start_timestamp, end_timestamp, segment);
    }
}

See examples/basic_use.rs for more details.

Lower level bindings are exposed if needed, but the above should be enough for most use cases. See the docs: https://docs.rs/whisper-rs/ for more details.

Building

See BUILDING.md for instructions for building whisper-rs on Windows and OSX M1. Linux builds should just work out of the box.

Troubleshooting

  • Something other than Windows/macOS/Linux isn't working!
    • I don't have a way to test this platforms, so I can't really help you.
      • If you can get it working, please open a PR with any changes to make it work and build instructions in BUILDING.md!
  • I get a panic during binding generation build!
    • You can attempt to fix it yourself, or you can set the WHISPER_DONT_GENERATE_BINDINGS environment variable. This skips attempting to build the bindings whatsoever and copies the existing ones. They may be out of date, but it's better than nothing.
      • WHISPER_DONT_GENERATE_BINDINGS=1 cargo build
    • If you can fix the issue, please open a PR!

License

Unlicense

tl;dr: public domain