test(transcription): GPU/CPU timing spike (opt-in) for whisper.cpp backends

src-tauri/src/transcription/mod.rs

@@ -296,4 +296,37 @@ mod tests {
     fn audio_ctx_is_capped_at_whispers_own_maximum() {
         assert_eq!(audio_ctx_for_window(60 * 16_000), 1500); // 60s window
     }
+
+    /// GPU spike (opt-in): times whisper.cpp on a chosen backend against a real
+    /// model + wav. With `--features vulkan` and `WA_BACKEND=intel` (or nvidia/amd)
+    /// whisper.cpp offloads to the GPU; `WA_BACKEND=cpu` is the baseline. Run:
+    ///   WA_WHISPER_MODEL=…ggml-base.en-q5_1.bin WA_TEST_WAV=…tts_test.wav \
+    ///   cargo test --features vulkan gpu_transcribes -- --ignored --nocapture
+    #[test]
+    #[ignore = "requires a whisper model + wav; GPU/CPU timing spike"]
+    fn gpu_transcribes_and_times() {
+        let model = std::env::var("WA_WHISPER_MODEL").expect("set WA_WHISPER_MODEL");
+        let wav = std::env::var("WA_TEST_WAV").expect("set WA_TEST_WAV");
+        let backend = match std::env::var("WA_BACKEND").as_deref() {
+            Ok("cpu") => BackendId::Cpu,
+            Ok("nvidia") => BackendId::Nvidia,
+            Ok("amd") => BackendId::Amd,
+            _ => BackendId::Intel, // use_gpu = true for any non-CPU backend
+        };
+        let t0 = std::time::Instant::now();
+        let transcriber = WhisperTranscriber::load(Path::new(&model), backend).expect("load");
+        let load_ms = t0.elapsed().as_millis();
+        let t1 = std::time::Instant::now();
+        let segments = transcriber
+            .transcribe_file(Path::new(&wav))
+            .expect("transcribe");
+        let infer_ms = t1.elapsed().as_millis();
+        let text = segments
+            .iter()
+            .map(|s| s.text.as_str())
+            .collect::<Vec<_>>()
+            .join(" ");
+        eprintln!("[spike] backend={backend:?} load={load_ms}ms infer={infer_ms}ms text={text:?}");
+        assert!(!text.trim().is_empty(), "transcript was empty");
+    }
 }