edison/chanora
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(audio): improve doc comments on key modules (TODO-031)

Browse Source 
Add/improve dart doc comments for frame converters, AudioEngineConfig,
VadOutput variants, WebRtcFallbackVad, SileroOnnxVad, AppleCoreMlVad.
This commit is contained in:
Edison Jwa
2026-06-11 13:31:12 +09:00
parent dd6fa6121e
commit 008128defc
4 changed files with 10 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/chanora_audio/src/engine/mod.rs
+1 -1
View File
@@ -361,7 +361,7 @@ pub fn list_audio_devices() -> AudioDeviceList {
} }
} }
/// Engine configuration. /// Engine configuration for the audio subsystem.
#[derive(Clone)] #[derive(Clone)]
pub struct AudioEngineConfig { pub struct AudioEngineConfig {
/// Input gain applied before encoding (1.0 = pass-through). /// Input gain applied before encoding (1.0 = pass-through).
crates/chanora_audio/src/frame.rs
+2 -2
View File
@@ -16,12 +16,12 @@ pub const FRAME_10MS_SAMPLES: usize = 480;
/// Samples in one 20 ms mono frame at 48 kHz. /// Samples in one 20 ms mono frame at 48 kHz.
pub const FRAME_20MS_SAMPLES: usize = 960; pub const FRAME_20MS_SAMPLES: usize = 960;
/// Convert i16 PCM to normalized f32 PCM. /// Convert i16 PCM sample to normalized f32 PCM (-1.0 to 1.0).
pub fn i16_to_f32(sample: i16) -> f32 { pub fn i16_to_f32(sample: i16) -> f32 {
sample as f32 / i16::MAX as f32 sample as f32 / i16::MAX as f32
} }
/// Convert normalized f32 PCM to saturated i16 PCM. /// Convert normalized f32 PCM to saturated i16 PCM (clamps to [-1.0, 1.0]).
pub fn f32_to_i16(sample: f32) -> i16 { pub fn f32_to_i16(sample: f32) -> i16 {
(sample.clamp(-1.0, 1.0) * i16::MAX as f32) as i16 (sample.clamp(-1.0, 1.0) * i16::MAX as f32) as i16
} }
crates/chanora_audio/src/vad/apple_coreml.rs
+2 -1
View File
@@ -89,7 +89,8 @@ unsafe fn resolve_symbol(name: &'static [u8]) -> Option<*mut c_void> {
} }
} }
/// 16 kHz detector backed by Swift `SileroCoreML.SileroVAD`. /// 16 kHz detector backed by Swift Silero CoreML VAD.
/// Processes 16 kHz frames and outputs speech probability.
pub struct AppleCoreMlVad { pub struct AppleCoreMlVad {
handle: *mut c_void, handle: *mut c_void,
symbols: AppleSileroSymbols, symbols: AppleSileroSymbols,
crates/chanora_audio/src/vad/mod.rs
+5 -3
View File
@@ -22,6 +22,7 @@ use resampler::{Downsampler48to16, INPUT_FRAME_10MS};
pub use silero_onnx::SileroOnnxVad; pub use silero_onnx::SileroOnnxVad;
/// Voice activity detector output for one 10 ms frame. /// Voice activity detector output for one 10 ms frame.
/// Contains speech probability and binary decision.
#[derive(Debug, Clone, Copy)] #[derive(Debug, Clone, Copy)]
pub struct VadOutput { pub struct VadOutput {
/// Speech confidence in the inclusive range `[0.0, 1.0]`. /// Speech confidence in the inclusive range `[0.0, 1.0]`.
@@ -36,7 +37,8 @@ pub trait VoiceActivityDetector: Send {
fn process_10ms(&mut self, samples: &[f32]) -> VadOutput; fn process_10ms(&mut self, samples: &[f32]) -> VadOutput;
} }
/// Realtime-safe WebRTC VAD used when a model runtime is unavailable. /// Realtime-safe WebRTC VAD fallback when ONNX runtime is unavailable.
/// Uses aggressive mode at 48 kHz for voice detection.
pub struct WebRtcFallbackVad { pub struct WebRtcFallbackVad {
vad: webrtc_vad::Vad, vad: webrtc_vad::Vad,
frame_i16: [i16; INPUT_FRAME_10MS], frame_i16: [i16; INPUT_FRAME_10MS],
@@ -75,8 +77,8 @@ impl VoiceActivityDetector for WebRtcFallbackVad {
} }
} }
/// Wraps any `VoiceActivityDetector` that operates at 16 kHz and /// Wraps any `VoiceActivityDetector` operating at 16 kHz,
/// downsamples 48 kHz input before forwarding. /// downsampling 48 kHz input before forwarding to the detector.
pub struct Resampled16kHzVad<D: VoiceActivityDetector> { pub struct Resampled16kHzVad<D: VoiceActivityDetector> {
inner: D, inner: D,
downsampler: Downsampler48to16, downsampler: Downsampler48to16,