b9819977a5
Includes prior-session patches (carry forward so the app compiles): - crates/gpui/build.rs: cross-compile manifest fix - crates/gpui/src/platform.rs: PlatformWindow::activate_with_token trait method - crates/gpui/src/window.rs: Window::activate_with_token public API - crates/gpui_linux/src/linux/wayland/window.rs: WaylandWindow::activate_with_token + activate() keyboard-serial fix Plus the focus-serial fix: - serial.rs: SerialKind::KeyboardEnter - client.rs: store wl_keyboard.enter serial; latest_serial_of() Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Real time streaming audio denoising using a Dual-Signal Transformation LSTM Network for Real-Time Noise Suppression.
Trivial to build as it uses the native rust Candle crate for inference. Easy to integrate into any Rodio pipeline.
# use rodio::{nz, source::UniformSourceIterator, wav_to_file};
let file = std::fs::File::open("clips_airconditioning.wav")?;
let decoder = rodio::Decoder::try_from(file)?;
let resampled = UniformSourceIterator::new(decoder, nz!(1), nz!(16_000));
let mut denoised = denoise::Denoiser::try_new(resampled)?;
wav_to_file(&mut denoised, "denoised.wav")?;
Result::Ok<(), Box<dyn std::error::Error>>
Acknowledgements & License
The trained models in this repo are optimized versions of the models in the breizhn/DTLN. These are licensed under MIT.
The FFT code was adapted from Datadog's dtln-rs Repo also licensed under MIT.