Fallback to CPU when CUDA STT runtime is missing

python/local_stt_worker.py

@@ -58,14 +58,36 @@ class SttWorker:
         from faster_whisper import WhisperModel
 
         self.model_name = os.environ.get("LOCAL_STT_MODEL", "tiny").strip() or "tiny"
-        self.device = resolve_device()
-        self.compute_type = resolve_compute_type(self.device)
+        requested_device = resolve_device()
+        requested_compute_type = resolve_compute_type(requested_device)
         self.beam_size = int(os.environ.get("LOCAL_STT_BEAM_SIZE", "1"))
-        self.model = WhisperModel(
-            self.model_name,
-            device=self.device,
-            compute_type=self.compute_type,
-        )
+        auto_requested = os.environ.get("LOCAL_STT_DEVICE", "auto").strip().lower() in {"", "auto"}
+
+        try:
+            self.model = WhisperModel(
+                self.model_name,
+                device=requested_device,
+                compute_type=requested_compute_type,
+            )
+            self.device = requested_device
+            self.compute_type = requested_compute_type
+        except RuntimeError as exc:
+            lowered = str(exc).lower()
+            should_fallback = auto_requested and requested_device == "cuda" and any(
+                token in lowered for token in ("cublas", "cudnn", "cuda")
+            )
+            if not should_fallback:
+                raise
+
+            log("CUDA runtime is incomplete; falling back to CPU STT")
+            self.model = WhisperModel(
+                self.model_name,
+                device="cpu",
+                compute_type=resolve_compute_type("cpu"),
+            )
+            self.device = "cpu"
+            self.compute_type = resolve_compute_type("cpu")
+
         log(
             f"local-stt ready model={self.model_name} device={self.device} compute={self.compute_type} beam={self.beam_size}"
         )