Update handler.py

handler.py

@@ -25,14 +25,10 @@ class EndpointHandler:
             return_tensors="pt",).to("cuda")
 
         # pass inputs with all kwargs in data
-        if parameters is not None:
-            with torch.autocast("cuda"):
-                outputs = self.model.generate(**inputs, **parameters)
-        else:
-            with torch.autocast("cuda"):
-                outputs = self.model.generate(**inputs,)
+        with torch.autocast("cuda"):
+                outputs = self.model.generate(**inputs, do_sample=False, max_new_tokens=400)
 
         # postprocess the prediction
-        prediction = outputs[0].cpu().numpy().tolist()
+        prediction = outputs[0].cpu().numpy().tobytes()
 
-        return [{"generated_audio": prediction}]
+        return prediction