citrinet-rs
| Crates.io | citrinet-rs |
| lib.rs | citrinet-rs |
| version | 0.1.0 |
| created_at | 2026-01-16 15:15:16.602608+00 |
| updated_at | 2026-01-16 15:15:16.602608+00 |
| description | Minimal Citrinet speech-to-text inference using ONNX Runtime and kaldi-native-fbank in Rust. |
| homepage | https://github.com/RustedBytes/citrinet-rs |
| repository | https://github.com/RustedBytes/citrinet-rs |
| max_upload_size | |
| id | 2048763 |
| size | 40,595 |
dev-team (github:iron:dev-team)
documentation
https://docs.rs/citrinet-rs
README
citrinet-rs
Minimal Citrinet inference example in Rust using ONNX Runtime (ort) and kaldi-native-fbank for feature extraction.
Run
cargo run --release -- \
--model model.onnx \
--tokens tokens.txt \
--audio test_wavs/0.wav
Inputs are expected to be mono 16 kHz WAV audio and a token file formatted as symbol index per line (batch size 1). Defaults match the sample paths above.