Reduce model initialization time for online speech recognition (#215)

* Reduce model initialization time for online speech recognition

* Fixed Styling

---------

Co-authored-by: w11wo <wilsowong961@gmail.com>

sherpa-onnx/c-api/c-api.h

@@ -53,6 +53,7 @@ SHERPA_ONNX_API typedef struct SherpaOnnxOnlineTransducerModelConfig {
   const char *tokens;
   int32_t num_threads;
   const char *provider;
+  const char *model_type;
   int32_t debug;  // true to print debug information of the model
 } SherpaOnnxOnlineTransducerModelConfig;