Encode hotwords in C++ side (#828)

* Encode hotwords in C++ side

sherpa-onnx/python/sherpa_onnx/online_recognizer.py

@@ -58,6 +58,8 @@ class OnlineRecognizer(object):
         hotwords_file: str = "",
         provider: str = "cpu",
         model_type: str = "",
+        modeling_unit: str = "cjkchar",
+        bpe_vocab: str = "",
         lm: str = "",
         lm_scale: float = 0.1,
         temperature_scale: float = 2.0,
@@ -136,6 +138,16 @@ class OnlineRecognizer(object):
           model_type:
             Online transducer model type. Valid values are: conformer, lstm,
             zipformer, zipformer2. All other values lead to loading the model twice.
+          modeling_unit:
+            The modeling unit of the model, commonly used units are bpe, cjkchar,
+            cjkchar+bpe, etc. Currently, it is needed only when hotwords are
+            provided, we need it to encode the hotwords into token sequence.
+          bpe_vocab:
+            The vocabulary generated by google's sentencepiece program.
+            It is a file has two columns, one is the token, the other is
+            the log probability, you can get it from the directory where
+            your bpe model is generated. Only used when hotwords provided
+            and the modeling unit is bpe or cjkchar+bpe.
         """
         self = cls.__new__(cls)
         _assert_file_exists(tokens)
@@ -157,6 +169,8 @@ class OnlineRecognizer(object):
             num_threads=num_threads,
             provider=provider,
             model_type=model_type,
+            modeling_unit=modeling_unit,
+            bpe_vocab=bpe_vocab,
             debug=debug,
         )