feat(npu): catalog the merged Whisper decoder (decoder_model_merged.onnx) for KV-cache decode (T3.4)

src-tauri/src/transcription/onnx_models.rs

@@ -15,9 +15,16 @@ const REPO: &str = "onnx-community/whisper-base.en";
 pub const DEFAULT_ONNX_MODEL: &str = "base.en";
 
 /// The four artifacts the `OnnxTranscriber` needs, relative to the repo root.
+/// The decoder is Optimum's *merged* export — both the no-past and with-past
+/// branches in one graph, selected by a `use_cache_branch` input — which is
+/// what enables the KV-cache decode loop (the plain `decoder_model.onnx`
+/// re-ran the whole prefix every step). Existing installs migrate for free:
+/// swapping this entry flips `is_installed` to false, the startup background
+/// fetch re-runs `download`, and `download` skips the three files already on
+/// disk, fetching only the merged decoder.
 const FILES: &[(&str, &str)] = &[
     ("encoder_model.onnx", "onnx/encoder_model.onnx"),
-    ("decoder_model.onnx", "onnx/decoder_model.onnx"),
+    ("decoder_model_merged.onnx", "onnx/decoder_model_merged.onnx"),
     ("tokenizer.json", "tokenizer.json"),
     ("generation_config.json", "generation_config.json"),
 ];
@@ -45,7 +52,7 @@ pub fn model_files(id: &str) -> OnnxModelFiles {
     let dir = onnx_dir(id);
     OnnxModelFiles {
         encoder: dir.join("encoder_model.onnx"),
-        decoder: dir.join("decoder_model.onnx"),
+        decoder: dir.join("decoder_model_merged.onnx"),
         tokenizer: dir.join("tokenizer.json"),
         generation_config: dir.join("generation_config.json"),
     }
@@ -125,6 +132,6 @@ mod tests {
     fn catalog_lists_the_four_required_artifacts() {
         assert_eq!(FILES.len(), 4);
         assert!(FILES.iter().any(|(n, _)| *n == "encoder_model.onnx"));
-        assert!(FILES.iter().any(|(n, _)| *n == "decoder_model.onnx"));
+        assert!(FILES.iter().any(|(n, _)| *n == "decoder_model_merged.onnx"));
     }
 }