feat(diarization): Diarizer::diarize_samples + short-input guard for masked far-side pass (FR-SPK)

src-tauri/src/diarization/mod.rs

@@ -23,6 +23,11 @@ pub enum DiarError {
 pub trait Diarizer: Send + Sync {
     /// Partition audio into speaker spans.
     fn diarize(&self, wav: &Path) -> Result<Vec<SpeakerSpan>, DiarError>;
+    /// Partition already-loaded 16kHz mono samples into speaker spans. Phase 3
+    /// (FR-SPK) diarizes a *masked* far-side signal (the mic's "You" ranges
+    /// zeroed), so the caller loads and masks the samples itself rather than
+    /// pointing at the raw WAV.
+    fn diarize_samples(&self, samples: Vec<f32>) -> Result<Vec<SpeakerSpan>, DiarError>;
     /// Assign speaker labels to transcript segments by overlap with spans.
     fn assign(&self, segments: &mut [TranscriptSegment], spans: &[SpeakerSpan]);
 }
@@ -92,6 +97,16 @@ impl Diarizer for SherpaDiarizer {
     fn diarize(&self, wav: &Path) -> Result<Vec<SpeakerSpan>, DiarError> {
         let samples =
             crate::audio::read_wav_mono_16k(wav).map_err(|e| DiarError::Run(e.to_string()))?;
+        self.diarize_samples(samples)
+    }
+
+    fn diarize_samples(&self, samples: Vec<f32>) -> Result<Vec<SpeakerSpan>, DiarError> {
+        // Guard the native FFI against degenerate input (a fully-masked far side
+        // is all zeros; a tiny buffer has no usable window). sherpa can crash
+        // rather than error on these, so skip cleanly instead.
+        if samples.len() < MIN_DIARIZE_SAMPLES {
+            return Ok(Vec::new());
+        }
         let mut engine = self.engine.lock().unwrap_or_else(|e| e.into_inner());
         let segments = engine
             .compute(samples, None)
@@ -116,6 +131,12 @@ impl Diarizer for SherpaDiarizer {
 #[cfg(feature = "diarization")]
 const MIN_SPAN_MS: u64 = 700;
 
+/// Below this many 16kHz samples (~1s) the diarizer skips the sherpa FFI: a
+/// fully-masked far side is all zeros and a tiny buffer has no usable
+/// segmentation window, either of which can crash the native code.
+#[cfg(feature = "diarization")]
+const MIN_DIARIZE_SAMPLES: usize = 16_000;
+
 /// A span is kept only if it lasts at least [`MIN_SPAN_MS`].
 #[cfg(feature = "diarization")]
 fn span_long_enough(span: &SpeakerSpan) -> bool {