pyin-1.0.1 has been yanked.

pYIN algorithm written in Rust

This crate provides a pitch estimate for each frame of the audio signal and a probability the frame is voiced region.

The implementation is based on librosa. For easy translation from Python + Numpy to Rust, the implementation is written on top of ndarray crate.

Build & Run

You can use this both as a executable binary and as a library (C shared library and Rust library).

cargo run --release <input_file> <output_npy_file> <fmin> <fmax> --frame_ms <frame length in miliseconds>

cargo build --release
./target/release/pyin <input_file> <output_npy_file> <fmin> <fmax> --frame_ms <frame length in miliseconds>

Supported audio files: the same as Creak crate.
- Multi-channel audio files are supported.
output file: npy file contains an ndarray (shape=(3, no. of channels in input audio, no. of frames), data=[f0_array, voiced_flag_array, voiced_probs_array])
If "-" is used as the output filename, the app will send output data to stdout.

The example is in test/test.c. To build and run it with GCC,

./compile_test.sh
LD_LIBRARY_PATH=target/release ./test_pyin

Add the following to your Cargo.toml:

[dependencies]
pyin = {git = "https://github.com/Sytronik/pyin-rs.git", tag = "v1.0.0"}