deepgeek/silero-vad
2
0
Fork 0
mirror of https://github.com/snakers4/silero-vad.git synced 2026-02-04 17:39:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #497 from rumbleFTW/fix/rust-example-v5

Browse Source 
fix: rust example for v5 checkpoint
This commit is contained in:
Alexander Veysov
2024-07-11 17:48:58 +03:00
committed by GitHub
parent df7de797a5 a7bd2dd38f
commit 181cdf92b6
2 changed files with 11 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
examples/rust-example/src/silero.rs
View File

@@ -1,13 +1,12 @@
use crate::utils;
use ndarray::{Array, Array2, ArrayBase, ArrayD, Dim, IxDynImpl, OwnedRepr};
use ndarray::{s, Array, Array2, ArrayBase, ArrayD, Dim, IxDynImpl, OwnedRepr};
use std::path::Path;
#[derive(Debug)]
pub struct Silero {
session: ort::Session,
sample_rate: ArrayBase<OwnedRepr<i64>, Dim<[usize; 1]>>,
h: ArrayBase<OwnedRepr<f32>, Dim<IxDynImpl>>,
c: ArrayBase<OwnedRepr<f32>, Dim<IxDynImpl>>,
state: ArrayBase<OwnedRepr<f32>, Dim<IxDynImpl>>,
}
impl Silero {
@@ -16,20 +15,17 @@ impl Silero {
model_path: impl AsRef<Path>,
) -> Result<Self, ort::Error> {
let session = ort::Session::builder()?.commit_from_file(model_path)?;
let h = ArrayD::<f32>::zeros([2, 1, 64].as_slice());
let c = ArrayD::<f32>::zeros([2, 1, 64].as_slice());
let state = ArrayD::<f32>::zeros([2, 1, 128].as_slice());
let sample_rate = Array::from_shape_vec([1], vec![sample_rate.into()]).unwrap();
Ok(Self {
session,
sample_rate,
h,
c,
state,
})
}
pub fn reset(&mut self) {
self.h = ArrayD::<f32>::zeros([2, 1, 64].as_slice());
self.c = ArrayD::<f32>::zeros([2, 1, 64].as_slice());
self.state = ArrayD::<f32>::zeros([2, 1, 128].as_slice());
}
pub fn calc_level(&mut self, audio_frame: &[i16]) -> Result<f32, ort::Error> {
@@ -37,18 +33,17 @@ impl Silero {
.iter()
.map(|x| (*x as f32) / (i16::MAX as f32))
.collect::<Vec<_>>();
let frame = Array2::<f32>::from_shape_vec([1, data.len()], data).unwrap();
let mut frame = Array2::<f32>::from_shape_vec([1, data.len()], data).unwrap();
frame = frame.slice(s![.., ..480]).to_owned();
let inps = ort::inputs![
frame,
std::mem::take(&mut self.state),
self.sample_rate.clone(),
std::mem::take(&mut self.h),
std::mem::take(&mut self.c)
]?;
let res = self
.session
.run(ort::SessionInputs::ValueSlice::<4>(&inps))?;
self.h = res["hn"].try_extract_tensor().unwrap().to_owned();
self.c = res["cn"].try_extract_tensor().unwrap().to_owned();
.run(ort::SessionInputs::ValueSlice::<3>(&inps))?;
self.state = res["stateN"].try_extract_tensor().unwrap().to_owned();
Ok(*res["output"]
.try_extract_raw_tensor::<f32>()
.unwrap()

2
examples/rust-example/src/vad_iter.rs
View File

@@ -20,7 +20,7 @@ impl VadIter {
pub fn process(&mut self, samples: &[i16]) -> Result<(), ort::Error> {
self.reset_states();
for audio_frame in samples.chunks_exact(self.params.frame_size_samples) {
let speech_prob = self.silero.calc_level(audio_frame)?;
let speech_prob: f32 = self.silero.calc_level(audio_frame)?;
self.state.update(&self.params, speech_prob);
}
self.state.check_for_last_speech(samples.len());