add python tests (#111)

sherpa-onnx/python/sherpa_onnx/offline_recognizer.py

@@ -18,20 +18,25 @@ def _assert_file_exists(f: str):
 
 
 class OfflineRecognizer(object):
-    """A class for offline speech recognition."""
+    """A class for offline speech recognition.
+
+    Please refer to the following files for usages
+     - https://github.com/k2-fsa/sherpa-onnx/blob/master/sherpa-onnx/python/tests/test_offline_recognizer.py
+     - https://github.com/k2-fsa/sherpa-onnx/blob/master/python-api-examples/offline-decode-files.py
+    """
 
     @classmethod
     def from_transducer(
-            cls,
-            encoder: str,
-            decoder: str,
-            joiner: str,
-            tokens: str,
-            num_threads: int,
-            sample_rate: int = 16000,
-            feature_dim: int = 80,
-            decoding_method: str = "greedy_search",
-            debug: bool = False,
+        cls,
+        encoder: str,
+        decoder: str,
+        joiner: str,
+        tokens: str,
+        num_threads: int,
+        sample_rate: int = 16000,
+        feature_dim: int = 80,
+        decoding_method: str = "greedy_search",
+        debug: bool = False,
     ):
         """
         Please refer to
@@ -59,7 +64,7 @@ class OfflineRecognizer(object):
           feature_dim:
             Dimension of the feature used to train the model.
           decoding_method:
-            Valid values are greedy_search, modified_beam_search.
+            Support only greedy_search for now.
           debug:
             True to show debug messages.
         """
@@ -68,14 +73,12 @@ class OfflineRecognizer(object):
             transducer=OfflineTransducerModelConfig(
                 encoder_filename=encoder,
                 decoder_filename=decoder,
-                joiner_filename=joiner
-            ),
-            paraformer=OfflineParaformerModelConfig(
-                model=""
+                joiner_filename=joiner,
             ),
+            paraformer=OfflineParaformerModelConfig(model=""),
             tokens=tokens,
             num_threads=num_threads,
-            debug=debug
+            debug=debug,
         )
 
         feat_config = OfflineFeatureExtractorConfig(
@@ -93,14 +96,14 @@ class OfflineRecognizer(object):
 
     @classmethod
     def from_paraformer(
-            cls,
-            paraformer: str,
-            tokens: str,
-            num_threads: int,
-            sample_rate: int = 16000,
-            feature_dim: int = 80,
-            decoding_method: str = "greedy_search",
-            debug: bool = False,
+        cls,
+        paraformer: str,
+        tokens: str,
+        num_threads: int,
+        sample_rate: int = 16000,
+        feature_dim: int = 80,
+        decoding_method: str = "greedy_search",
+        debug: bool = False,
     ):
         """
         Please refer to
@@ -131,16 +134,12 @@ class OfflineRecognizer(object):
         self = cls.__new__(cls)
         model_config = OfflineModelConfig(
             transducer=OfflineTransducerModelConfig(
-                encoder_filename="",
-                decoder_filename="",
-                joiner_filename=""
-            ),
-            paraformer=OfflineParaformerModelConfig(
-                model=paraformer
+                encoder_filename="", decoder_filename="", joiner_filename=""
             ),
+            paraformer=OfflineParaformerModelConfig(model=paraformer),
             tokens=tokens,
             num_threads=num_threads,
-            debug=debug
+            debug=debug,
         )
 
         feat_config = OfflineFeatureExtractorConfig(
@@ -164,4 +163,3 @@ class OfflineRecognizer(object):
 
     def decode_streams(self, ss: List[OfflineStream]):
         self.recognizer.decode_streams(ss)
-