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

fix(audio): use WebRTC VAD on iOS

Browse Source
This commit is contained in:
Edison Jwa
2026-05-31 22:30:28 +09:00
parent c02d4e6df3
commit 6f7063971d
6 changed files with 119 additions and 189 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/chanora_audio/src/ios_raw_unit.rs
+9 -57
View File
@@ -116,9 +116,7 @@ mod inner {
mic_gain: f32,
voice_activity_selector: Option<Arc<crate::TransmitModeSelector>>,
vad_detector: crate::vad::WebRtcFallbackVad,
silero_vad_worker: Option<crate::vad::silero_onnx::SileroOnnxVadWorker>,
current_vad_backend: crate::VadBackend,
silero_model_epoch: u64,
capture_frame_seq: u64,
vad_state: crate::voice_activity::VoiceActivityStateMachine,
/// Processing config — retained for route-change reloads.
@@ -154,9 +152,7 @@ mod inner {
mic_gain: params.mic_gain,
voice_activity_selector: params.voice_activity_selector.clone(),
vad_detector: crate::vad::WebRtcFallbackVad::default(),
silero_vad_worker: None,
current_vad_backend: crate::VadBackend::WebrtcVad,
silero_model_epoch: crate::vad::silero_model_epoch(),
capture_frame_seq: 0,
vad_state: crate::voice_activity::VoiceActivityStateMachine::default(),
audio_processing_config: params.audio_processing_config.clone(),
@@ -276,7 +272,6 @@ mod inner {
.map(|selector| selector.mode() == crate::TransmitMode::VoiceActivity)
.unwrap_or(false);
if !voice_activity_mode {
self.silero_vad_worker = None;
self.current_vad_backend = crate::VadBackend::Disabled;
self.fallback_warned_backend = None;
self.audio_processing_stats.set_vad_fallback_active(false);
@@ -298,37 +293,20 @@ mod inner {
);
}
// Switch VAD backend only while VoiceActivity mode is active.
let silero_epoch = crate::vad::silero_model_epoch();
let silero_changed = voice_activity_mode
&& vad_backend == crate::VadBackend::SileroOnnx
&& silero_epoch != self.silero_model_epoch;
if voice_activity_mode && (vad_backend != self.current_vad_backend || silero_changed) {
if voice_activity_mode && vad_backend != self.current_vad_backend {
self.current_vad_backend = vad_backend;
self.silero_model_epoch = silero_epoch;
self.fallback_warned_backend = None;
match vad_backend {
crate::VadBackend::SileroOnnx => {
let path = crate::vad::silero_model_bundle_path();
self.silero_vad_worker =
crate::vad::silero_onnx::SileroOnnxVadWorker::try_new(&path);
if self.silero_vad_worker.is_none() {
tracing::warn!(
target: "chanora_audio",
"Silero VAD model not found at {path}; falling back to WebRTC VAD"
);
}
}
_ => {
self.silero_vad_worker = None;
}
if vad_backend == crate::VadBackend::SileroOnnx {
self.mark_vad_fallback_active(crate::VadBackend::SileroOnnx);
self.audio_processing_stats.set_vad_fallback_active(true);
} else {
self.audio_processing_stats.set_vad_fallback_active(false);
}
self.vad_state.reset();
}
let (vad_probability, active) = if voice_activity_mode {
self.capture_frame_seq = self.capture_frame_seq.wrapping_add(1);
let capture_seq = self.capture_frame_seq;
let mut used_fallback_vad = false;
let vad = if vad_backend == crate::VadBackend::Disabled {
crate::vad::VadOutput {
@@ -336,35 +314,9 @@ mod inner {
speech: true,
}
} else if vad_backend == crate::VadBackend::SileroOnnx {
if let Some(worker) = self.silero_vad_worker.as_ref() {
let enqueued = worker.try_send(capture_seq, &frame);
if !worker.is_stale(capture_seq) {
let p = worker.latest_probability();
crate::vad::VadOutput {
probability: p,
speech: p >= 0.5,
}
} else if enqueued {
crate::vad::VadOutput {
probability: 0.0,
speech: false,
}
} else {
used_fallback_vad = true;
self.mark_vad_fallback_active(vad_backend);
crate::vad::VoiceActivityDetector::process_10ms(
&mut self.vad_detector,
&frame,
)
}
} else {
used_fallback_vad = true;
self.mark_vad_fallback_active(vad_backend);
crate::vad::VoiceActivityDetector::process_10ms(
&mut self.vad_detector,
&frame,
)
}
used_fallback_vad = true;
self.mark_vad_fallback_active(vad_backend);
crate::vad::VoiceActivityDetector::process_10ms(&mut self.vad_detector, &frame)
} else {
crate::vad::VoiceActivityDetector::process_10ms(&mut self.vad_detector, &frame)
};