src-tauri/src/transcription/npu.rs

@@ -202,7 +202,24 @@ impl Transcriber for OnnxTranscriber {
     /// `Npu` → OpenVINO EP; `Amd`/`Intel` → DirectML EP (the non-Vulkan GPU
     /// path). Any other value is rejected so the dispatcher can fall back to
     /// whisper.cpp rather than us guessing.
-    fn load(model: &Path, backend: BackendId) -> Result<Self, TrxError> {
+    ///
+    /// `language` (T8.7, FR-TRX-4): the exported ONNX model's
+    /// `forced_decoder_ids` bakes its language in at export time — this
+    /// engine has no per-inference language selection to apply, unlike
+    /// whisper.cpp's `FullParams::set_language`. A non-English, non-auto
+    /// request is logged (not silently dropped) so a user picking a language
+    /// on the NPU/DirectML path finds out it didn't take, rather than
+    /// getting a quietly-wrong transcript; `effective_language`/
+    /// `detected_language` fall back to the trait's English-only defaults.
+    fn load(model: &Path, backend: BackendId, language: Option<&str>) -> Result<Self, TrxError> {
+        if let Some(lang) = language {
+            if !lang.eq_ignore_ascii_case("auto") && !lang.eq_ignore_ascii_case("en") {
+                tracing::warn!(
+                    "language '{lang}' requested but the NPU/DirectML engine's ONNX model is \
+                     English-only (language is fixed at export time); ignoring the request"
+                );
+            }
+        }
         // Pick the runtime bundle + encoder EP for the requested accelerator.
         // error_on_failure makes a failed accelerator registration LOUD (Err)
         // instead of a silent CPU fallback, so the dispatcher can cleanly drop
@@ -465,7 +482,7 @@ mod tests {
         };
         let wav = std::env::var("WA_NPU_TEST_WAV").expect("set WA_NPU_TEST_WAV");
         let t0 = std::time::Instant::now();
-        let t = OnnxTranscriber::load(Path::new(&model_dir), BackendId::Npu)
+        let t = OnnxTranscriber::load(Path::new(&model_dir), BackendId::Npu, None)
             .expect("load NPU transcriber");
         let load_ms = t0.elapsed().as_millis();
         let t1 = std::time::Instant::now();
@@ -507,7 +524,8 @@ mod tests {
             _ => BackendId::Intel,
         };
         let t0 = std::time::Instant::now();
-        let t = OnnxTranscriber::load(Path::new(&model_dir), backend).expect("load DirectML");
+        let t =
+            OnnxTranscriber::load(Path::new(&model_dir), backend, None).expect("load DirectML");
         let load_ms = t0.elapsed().as_millis();
         let t1 = std::time::Instant::now();
         let segs = t.transcribe_file(Path::new(&wav)).expect("transcribe");