add kwargs to all the model implemnetations

birdnet_custom_v2.4/model.py

@@ -49,6 +49,7 @@ class Model(ModelBase):
         model_path: str = None,
         sigmoid_sensitivity: float = 1.0,
         num_threads: int = 1,
+        **kwargs 
     ):
 
         self.default_model_path = str(Path(default_model_path) / "model.tflite")
@@ -78,6 +79,7 @@ class Model(ModelBase):
             labels_path=classifier_labels_path,
             num_threads=num_threads,
             sensitivity=sigmoid_sensitivity,
+            **kwargs
         )
 
     def load_model(self):

birdnet_custom_v2.4/preprocessor.py

@@ -14,6 +14,7 @@ class Preprocessor(ppb.PreprocessorBase):
         overlap: float = 0.0,
         sample_secs: int = 3.0,
         resample_type: str = "kaiser_fast",
+        **kwargs
     ):
         """
         __init__ Construct a new preprocesssor for custom birdnet classifiers from given parameters, and use defaults for the ones not present.
@@ -31,6 +32,7 @@ class Preprocessor(ppb.PreprocessorBase):
             overlap=overlap,
             sample_secs=sample_secs,
             resample_type=resample_type,
+            **kwargs
         )
 
     def process_audio_data(self, rawdata: np.ndarray) -> list:

birdnet_default_v2.4/model.py

@@ -18,6 +18,7 @@ class Model(ModelBase):
         num_threads: int = 1,
         sigmoid_sensitivity: float = 1.0,
         species_list_file: str = None,
+        **kwargs
     ):
         """
         __init__ Create a new model instance that uses birdnet-analyzer models for bird species classification
@@ -43,6 +44,7 @@ class Model(ModelBase):
             labels_path,
             num_threads=num_threads,
             sensitivity=sigmoid_sensitivity,
+            **kwargs
         )
 
         # store input and output index to not have to retrieve them each time an inference is made

birdnet_default_v2.4/preprocessor.py

@@ -14,6 +14,7 @@ class Preprocessor(ppb.PreprocessorBase):
         overlap: float = 0.0,
         sample_secs: int = 3.0,
         resample_type: str = "kaiser_fast",
+        **kwargs
     ):
         """
         __init__ Construct a new preprocesssor for custom birdnet classifiers from given parameters, and use defaults for the ones not present.
@@ -31,6 +32,7 @@ class Preprocessor(ppb.PreprocessorBase):
             overlap=overlap,
             sample_secs=sample_secs,
             resample_type=resample_type,
+            **kwargs
         )
 
     def process_audio_data(self, rawdata: np.ndarray) -> list:

google_bird_classification/model.py

@@ -7,7 +7,7 @@ import pandas as pd
 
 class Model(ModelBase):
 
-    def __init__(self, model_path: str, num_threads: int = 1, species_list_file=None):
+    def __init__(self, model_path: str, num_threads: int = 1, species_list_file=None, **kwargs):
         """
         __init__ Create a new Model instance using the google perch model.
 
@@ -26,6 +26,7 @@ class Model(ModelBase):
             model_path,
             labels_path,
             num_threads=num_threads,
+            **kwargs
             # sensitivity kwarg doesn't exist here
         )  # num_threads doesn't do anything here.
 

google_bird_classification/preprocessor.py

@@ -35,6 +35,7 @@ class Preprocessor(ppb.PreprocessorBase):
             sample_rate=sample_rate,
             sample_secs=sample_secs,
             resample_type=resample_type,
+            **kwargs
         )
 
     def process_audio_data(self, rawdata: np.array) -> np.array: